The Spanish Grid Drop-out - recently released information....

[Carlos E.R.]

On 2025-05-13 06:25, Bill Sloman wrote:

On 13/05/2025 3:35 am, john larkin wrote:
On Sun, 11 May 2025 12:22:11 +1000, Chris Jones
lugnut808@spam.yahoo.com> wrote:

On 11/05/2025 5:04 am, john larkin wrote:

As solar and wind get to be dominant, micromanagement of power sources
and loads will be necessary to ensure uptime.

This is largely unnecessary - if the control signal that was being sent
out by the central controller to micromanage each power source was
derived from a function of the frequency, phase, voltage etc., then
rather than trying to distribute the result of this calculation to
millions of devices with low latency, it is better to distribute just
the formula (once every few years or as necessary), and run it on a
microcontroller in the inverters several times every mains cycle. They
already have more than enough processing power.

A central (international!) controller would want to know what every
contributor was pushing into the grid, and probably see wind flow and
clouds moving around. One local transmission line could fail and take
down half of Europe. Again.

What makes you think that?
The current control system clearly isn\'t that well informed, and it
works pretty much all the time.

I believe that there are some new regulatuions in at least one
Australian
state, driven by the (fossil-fuel-stoked) fear of \"too much solar
destabilising the grid\", which require new home solar inverters to stop
exporting power, unless they receive continuous \"permission to export\"
signals from our overlords, the network operators. In other words,
rather than exporting power in the case of communications failure, it
goes into the state of \"export no power\" in case of communications
failure, because otherwise people might unplug their internet to export
more scary solar power if exporting power was allowed when the internet
connection fails.

This is nonsense. The Australian grid don\'t like having to deal with
excess power being exported by roof-top solar installation, and
discourage people from doing it, to the point where 40% of new roof-top
solar installations in Australia include a Tesla Powerwall or an
equivalent battery, and don\'t export anything.

This is a fairly new requirement, so not many
compliant devices are installed now, but once a few gigawatts of these
inverters are running, it will be interesting to see what happens when
there is a major internet outage on a hot summer day, and all of those
gigawatts suddenly go away. Hopefully they thought of that but I
doubt it.

The rapid control algorithms should be distributed, and the only
low-latency communication signals they should rely upon are frequency
and voltage.

A solar panel with an algorithm can\'t know about potential system
overloads. Solar and wind will have to be shed sometimes to protect
the entire system. Loads shed too. Renewable-heavy grids are fragile.

The existing system doesn\'t know about potential system overloads, and
it works pretty much all the time. Regular grids are fragile too.

The renewable-heavy grid in South Australia was fragile, until they
bought the world first grid scale battery in 2017.

https://hornsdalepowerreserve.com.au/

They promptly devoted half the battery to short term phase correction
and frequency satabilisation, and it isn\'t fragile any more.

Carlos says that the Spanish mainland grid hasn\'t got any storage - no
grid battery and no pumped hydro, which is a bit silly.

No, no grid batteries yet. Pumped hydro there is somewhere; some island
have it for sure, it has gone an entire month on renewables alone.

I asked chatgpt:

Does the Spanish electricity network has storage capability?

Yes, the Spanish electricity network does have storage capabilities, but
on a limited scale relative to its overall electricity demand and
production.


*Key Points:*

1. Pumped Hydro Storage

This is the main form of energy storage in Spain. It\'s a mature and
widely used technology that involves pumping water uphill to a reservoir
during times of low electricity demand and releasing it to generate
electricity during peak demand.

Spain has several pumped hydro plants, including:

La Muela II (one of the largest in Europe)

Estany Gento-Sallente

Total pumped hydro storage capacity in Spain is estimated to be
around 6 GW (gigawatts) of installed capacity.

2. Battery Storage

Grid-scale battery storage is still in early development in Spain
but is growing.

Projects have been announced or launched, particularly to
complement renewable energy (especially solar and wind).

As of recent years, installed battery capacity is relatively small
(in the tens to hundreds of megawatts), but it\'s expected to grow
significantly under Spain’s energy transition plans.

3. Other Technologies

Thermal storage: Used in concentrated solar power (CSP) plants,
where molten salts store heat that can be used to generate electricity
after the sun goes down.

Hydrogen: In development, with pilot projects aiming to use green
hydrogen for seasonal or long-duration storage.

4. Future Plans

Spain\'s National Energy and Climate Plan (NECP) and other strategic
documents aim to:

Expand storage to around 20 GW by 2030, including batteries, pumped
hydro, and other technologies.

Enable better integration of intermittent renewables like wind and
solar.

Conclusion:

Yes, Spain\'s electricity network has storage capabilities, primarily
through pumped hydro, with growing use of batteries and thermal storage.
Significant expansion is planned to support the country\'s renewable
energy targets and grid stability.

--
Cheers, Carlos.

 

[Glen Walpert]

On Mon, 12 May 2025 23:25:12 +0200, Jeroen Belleman wrote:

On 5/12/25 21:42, Don Y wrote:
On 5/12/2025 7:31 AM, Theo wrote:
A naive question: why do we need to get these signals from the grid at
all?
Why can\'t we broadcast a synchronisation message on something like LW
radio that is picked up by every generator large or small?  Then the
network operator can monitor what\'s happening and adjust the signal as
appropriate.

How have we managed to distribute electrical power over huge swaths of
land from multiple independent operators WITHOUT such a mechanism?

I don\'t think that using broadcast radio for real time mains grid
control is a good idea. It would be far too unreliable.

Point to point RF links have been in use in (mostly hard wired) grid
control SCADA (System Control And Data Acquisition) systems for at least
30 years, which is when a former employer did some work on a SCADA upgrade
project for the Egyptian Electrical Authority. A search on \'SCADA radio
link\' will turn up several vendors.

To first order, power plants adjust the power injected into the grid by
observing the grid frequency. When the frequency drops, the injected
power is increased.

And when the voltage drops injected reactive power is increased.

Basler is a major manufacturer of generator controls for grid connected
generators, and they have available to anyone supplying a verifiable
company email a \'Technical Paper: Genset Control and Protection\'
under technical resources tab of:

https://www.basler.com/Product/DGC-2020-Digital-Genset-Controller

Being 10 years retired and having notes from a Basler 3 week course in
generator control and protective relaying I did not download it but it is
probably a good overview.

UL also has an overview of worldwide grid connect standards available for
email address - \'UL Grid Code Compliance eBook\' search should turn it up,
you will need a list of protective relay numbers to interpret it.

The most interesting of protective relays is 21, the distance relay,
absolutely essential for grid coordination (tripping only the breaker
closest to the fault).

https://www.researchgate.net/publication/
4333315_Fundamentals_of_Distance_Protection

This says nothing about the dynamic behavior, which is far more
involved, and variable too. Apparently there are some issues with that
on the European grid.

Eventually those issues will be discussed in detail in the trade press if
not elsewhere.

Jeroen Belleman

[Snip...]

 

[john larkin]

On Tue, 13 May 2025 12:57:47 +0200, \"Carlos E.R.\"
<robin_listas@es.invalid> wrote:

On 2025-05-13 06:25, Bill Sloman wrote:
On 13/05/2025 3:35 am, john larkin wrote:
On Sun, 11 May 2025 12:22:11 +1000, Chris Jones
lugnut808@spam.yahoo.com> wrote:

On 11/05/2025 5:04 am, john larkin wrote:

As solar and wind get to be dominant, micromanagement of power sources
and loads will be necessary to ensure uptime.

This is largely unnecessary - if the control signal that was being sent
out by the central controller to micromanage each power source was
derived from a function of the frequency, phase, voltage etc., then
rather than trying to distribute the result of this calculation to
millions of devices with low latency, it is better to distribute just
the formula (once every few years or as necessary), and run it on a
microcontroller in the inverters several times every mains cycle. They
already have more than enough processing power.

A central (international!) controller would want to know what every
contributor was pushing into the grid, and probably see wind flow and
clouds moving around. One local transmission line could fail and take
down half of Europe. Again.

What makes you think that?
The current control system clearly isn\'t that well informed, and it
works pretty much all the time.

I believe that there are some new regulatuions in at least one
Australian
state, driven by the (fossil-fuel-stoked) fear of \"too much solar
destabilising the grid\", which require new home solar inverters to stop
exporting power, unless they receive continuous \"permission to export\"
signals from our overlords, the network operators. In other words,
rather than exporting power in the case of communications failure, it
goes into the state of \"export no power\" in case of communications
failure, because otherwise people might unplug their internet to export
more scary solar power if exporting power was allowed when the internet
connection fails.

This is nonsense. The Australian grid don\'t like having to deal with
excess power being exported by roof-top solar installation, and
discourage people from doing it, to the point where 40% of new roof-top
solar installations in Australia include a Tesla Powerwall or an
equivalent battery, and don\'t export anything.

This is a fairly new requirement, so not many
compliant devices are installed now, but once a few gigawatts of these
inverters are running, it will be interesting to see what happens when
there is a major internet outage on a hot summer day, and all of those
gigawatts suddenly go away. Hopefully they thought of that but I
doubt it.

The rapid control algorithms should be distributed, and the only
low-latency communication signals they should rely upon are frequency
and voltage.

A solar panel with an algorithm can\'t know about potential system
overloads. Solar and wind will have to be shed sometimes to protect
the entire system. Loads shed too. Renewable-heavy grids are fragile.

The existing system doesn\'t know about potential system overloads, and
it works pretty much all the time. Regular grids are fragile too.

The renewable-heavy grid in South Australia was fragile, until they
bought the world first grid scale battery in 2017.

https://hornsdalepowerreserve.com.au/

They promptly devoted half the battery to short term phase correction
and frequency satabilisation, and it isn\'t fragile any more.

Carlos says that the Spanish mainland grid hasn\'t got any storage - no
grid battery and no pumped hydro, which is a bit silly.

No, no grid batteries yet. Pumped hydro there is somewhere; some island
have it for sure, it has gone an entire month on renewables alone.

I asked chatgpt:

Does the Spanish electricity network has storage capability?

Yes, the Spanish electricity network does have storage capabilities, but
on a limited scale relative to its overall electricity demand and
production.


*Key Points:*

1. Pumped Hydro Storage

This is the main form of energy storage in Spain. It\'s a mature and
widely used technology that involves pumping water uphill to a reservoir
during times of low electricity demand and releasing it to generate
electricity during peak demand.

Spain has several pumped hydro plants, including:

La Muela II (one of the largest in Europe)

Estany Gento-Sallente

Total pumped hydro storage capacity in Spain is estimated to be
around 6 GW (gigawatts) of installed capacity.

2. Battery Storage

Grid-scale battery storage is still in early development in Spain
but is growing.

Projects have been announced or launched, particularly to
complement renewable energy (especially solar and wind).

As of recent years, installed battery capacity is relatively small
(in the tens to hundreds of megawatts), but it\'s expected to grow
significantly under Spain’s energy transition plans.

3. Other Technologies

Thermal storage: Used in concentrated solar power (CSP) plants,
where molten salts store heat that can be used to generate electricity
after the sun goes down.

Hydrogen: In development, with pilot projects aiming to use green
hydrogen for seasonal or long-duration storage.

4. Future Plans

Spain\'s National Energy and Climate Plan (NECP) and other strategic
documents aim to:

Expand storage to around 20 GW by 2030, including batteries, pumped
hydro, and other technologies.

Enable better integration of intermittent renewables like wind and
solar.

Conclusion:

Yes, Spain\'s electricity network has storage capabilities, primarily
through pumped hydro, with growing use of batteries and thermal storage.
Significant expansion is planned to support the country\'s renewable
energy targets and grid stability.

Renewable and stable conflict. Both are expensive.

Pumped hydro is 70 to 80% efficient, but can\'t be located just
anywhere, so add transmission line losses. And there\'s a limit to how
much can be built.

Thermal storage is usually less efficient.

Batteries are big and expensive and often dangerous. Backing up a
country for a week is basically impossible.

Nukes are great, but not if you tear them down.

Lots of money is being spent to (mostly not) fix a problem that used
to not exist. If Europe wants to shiver in the dark and
de-industrialize, it\'s fine with us. And with China.

Germany and Japan lost WWII largely because they ran out of energy
resources, and the US didn\'t. Now europe is voluntarily wrecking
itself. When unemployed people get cold and hungry in the dark,
politics will change. The left will put up a big fight but will lose.

 

[john larkin]

On Tue, 13 May 2025 02:50:21 +0200, \"Carlos E.R.\"
<robin_listas@es.invalid> wrote:

On 2025-05-13 00:20, Joe Gwinn wrote:
On Mon, 12 May 2025 23:33:30 +0200, \"Carlos E.R.\"
robin_listas@es.invalid> wrote:

On 2025-05-12 16:36, Martin Brown wrote:
On 10/05/2025 17:58, John Robertson wrote:
On 2025-05-10 9:46 a.m., Bill Sloman wrote:

...

Perhaps for systems that have large solar or wind arrays they could
use a number of large rotating masses to smooth over these burps?
Vacuum and magnetic bearings...

They are intrinsically dangerous if they store enough energy to really
matter. We had such a steel reinforced lead flywheel and motor generator
configuration on big radio telescopes storing just enough energy to stow
them in the event of a storm taking out 3 phase mains power. The dishes
can only reliably survive storms if they are pointed at the zenith.
(sometimes not even then)

Working out how far it would travel if it ever broke free from its very
substantial bearings was used as an exam question. It was installed
pointing so that it would not hit any property if it did.

It would affect earth rotation, too. Some huge water reservoir in China
is affecting it already.

Three Gorges Dam?

.<https://en.wikipedia.org/wiki/Three_Gorges_Dam

Yep.

Estimated at 60 ns/day, similar to the effect of the moon, except that
the moon\'s deceleration effect is cumulative.

 

[Don Y]

On 5/13/2025 6:26 AM, Glen Walpert wrote:

I don\'t think that using broadcast radio for real time mains grid
control is a good idea. It would be far too unreliable.

Point to point RF links have been in use in (mostly hard wired) grid
control SCADA (System Control And Data Acquisition) systems for at least
30 years, which is when a former employer did some work on a SCADA upgrade
project for the Egyptian Electrical Authority. A search on \'SCADA radio
link\' will turn up several vendors.

And they used these to control instantaneous frequency and phase? Or, just
coarse data collection and /supervisory/ control?

 

[KevinJ93]

On 5/12/25 2:47 PM, Martin Brown wrote:

On 12/05/2025 18:35, john larkin wrote:
...

They are all connected to the national grid. The grid frequency target
and voltage is extremely well known and all that is needed is for each
unit that can to try and drive the grid voltage and frequency towards
that target. Things get iffy when they drop out a lot of stuff all at
once because they are using the same rules and rapid collapse follows.

That\'s what the California RUle 21 for Solar Inverters attempts.

As the frequency rises above 60Hz the inverter linearly reduces its
power output to assist in grid stability. Similar actions apply as the
voltage increases. There are additional rules for how the unit is to
reconnect after a grid failure.

Future versions of the rules will include remote monitoring and control
but currently they are purely based on local grid frequency and voltage.

<...>

 

[Glen Walpert]

On Tue, 13 May 2025 07:50:36 -0700, Don Y wrote:

On 5/13/2025 6:26 AM, Glen Walpert wrote:
I don\'t think that using broadcast radio for real time mains grid
control is a good idea. It would be far too unreliable.

Point to point RF links have been in use in (mostly hard wired) grid
control SCADA (System Control And Data Acquisition) systems for at
least 30 years, which is when a former employer did some work on a
SCADA upgrade project for the Egyptian Electrical Authority. A search
on \'SCADA radio link\' will turn up several vendors.

And they used these to control instantaneous frequency and phase? Or,
just coarse data collection and /supervisory/ control?

SCADA is used to monitor and control the grid, where control is done in
real time by adjusting the set points for real and reactive power at all
controlled power sources. A small percentage of sources being
inaccessible degrades control by an insignificant amount.

Real power is regulated by the prime mover governors, which must be
operated in droop mode in order to share the load (the speed set point is
reduced with increasing load). The grid Hz/Gw figure which has been
mentioned is not directly related to generator inertia, where
insignificant energy is stored, it is the aggregate droop setting of the
prime mover governors feeding the grid. After speed/frequency shift (the
governors only measure shaft speed) due to a load change the grid control
center adjusts the governor set points to bring the frequency back to
normal.

Voltage regulation is entirely separate and is done by setting the
reactive power output of sources, again by adjusting set points in real
time over SCADA (or one of the other approved standard comm protocols).
This is a bit complex for a quick explanation but is described in detail
in any decent text covering synchronous generator control.

Voltage regulation is more likely to be a stability issue than frequency.
If you take two widely separated generators or sets of locally paralleled
generators at two power plants which are optimally tuned for stand alone
operation and connect them with a long transmission line, voltage will
begin to oscillate due to the time delay in locally detecting changes in
the other plants output. Detuning the regulators to achieve stability
results in inadequate response to load changes - thus central control of
both plants over SCADA.

Large generator voltage response time is limited by the L/R time constant,
which will be in the 10\'s of seconds, over a minute for some large multi-
pole hydroelectric generators. Inverters can respond much faster, with
potentially worse stability issues, and dividing power sources into many
small units does not make stability any easier, you still can\'t set
optimal tuning parameters for widely separated groups of sources which
will be both stable and fast, central control of some percentage of source
set points is required. This problem and it\'s solution is well understood
and the current generation of inverters are designed to allow remote
control of set points.

In the US more than 2/3 of all solar power is utility owned 10 MW or
larger and all of this is under central grid operator control, so no
stability issues there.

More intermittent power sources need more batteries, which are being
deployed by utilities as fast as they can be manufactured, being far
cheaper then peaking gas turbines, the most expensive of power sources.

<https://www.tdworld.com/distributed-energy-resources/energy-storage/news/
55287560/us-energy-storage-industry-commits-100-billion-investment-in-
american-made-grid-batteries>

Glen

 

[john larkin]

On Tue, 13 May 2025 22:28:23 +0200, \"Carlos E.R.\"
<robin_listas@es.invalid> wrote:

On 2025-05-13 18:14, Bill Sloman wrote:
On 13/05/2025 11:48 pm, john larkin wrote:
On Tue, 13 May 2025 12:57:47 +0200, \"Carlos E.R.\"
robin_listas@es.invalid> wrote:


Nukes are great, but not if you tear them down.

Nukes are remarkably expensive, and depressingly inflexible. Radiation
damage to the structure means that you do have to tear them down after a
few decades of use, and the radioactive waste starts off very
radioactive, and the longer-lived isotopes have to be managed for a few
hundred thousand years.

And the investors building the stations do not consider the cost of
managing the waste for centuries. They leave that part to the
government. In Spain, we don\'t have any long term nuclear waste storage.
I think we rent storage in France, so the waste has to be transported
there. We have some storage at each station, a large water pool.

The best thing to do with used fuel rods is reprocess them into more
fuel.

When that\'s not feasible, dig a deep hole and dump it in. Or drop
barrels of junk into an ocean subduction zone.

It\'s irrational to store nuclear waste locally. Nuke policy is mostly
fear driven. And nukes are unpopular in some quarters by people who
really don\'t want us to have affordable, safe energy.

 

[Carlos E.R.]

On 2025-05-10 18:46, Bill Sloman wrote:

One of my LinkedIn contacts - an IEEE contact in this case - posted some
new data on LinkedIn, from a \"Simon Gallagher, Managing Director at UK
Networks Services | CEng | FIET | FEI | MBA \"

Today the ministry said that they have ruled out a hacking of the REE,
but not in other places. And that it originated in Granada, Badajoz and
Sevilla (loss of generation).

Spanish:

<https://www.eldiario.es/economia/aagesen-avanza-desconexiones-generacion-apagon-empezaron-granada-badajoz-sevilla_1_12297171.html>

Aagesen says that the generation disconnections before the blackout
began in Granada, Badajoz and Seville.

They began with a substation in Granada and then occurred in
Badajoz and Seville; the vice-president speaks of ‘overvoltage’
problems, rules out a cyber-attack on Red Eléctrica and stresses that
‘hypotheses have already been ruled out’: it was not a problem of
coverage, reserve ‘or the size of the networks’.

The Third Vice-President and Minister for Ecological Transition, Sara
Aagesen, announced this Wednesday in the Congress of Deputies that the
generation losses prior to the historic blackout on 28 April ‘began in
Granada, Badajoz and Seville’. Aagesen, who confirmed that a
cyber-attack on Red Eléctrica has been ruled out, spoke of problems of
‘overvoltage’ in the system and explained that they are analysing
whether the oscillations detected in Europe half an hour before the cut
were related to the incident.

In an appearance in the plenary session to explain the crisis, the
vice-president explained that, after ‘at least two periods of
oscillations’ in the 30 minutes prior to the blackout, which were
detected in the peninsular and European system, with “low” demand at
that time, there were ‘three losses’ of generation: the first, ‘in a
substation in Granada’ at 12 hours, 32 minutes and 57 seconds; 19
seconds later, another substation in Badajoz was disconnected; and 20.3
seconds later, another in Seville. ‘The sum of these three events’
accumulated a loss of just over 2.2 gigawatts ‘in 20 seconds’.

The committee investigating the blackout is analyzing “disconnections
that may be due to overvoltage as a triggering element of the cascading
drop” that came just after. The control systems of the different
operators reflect that that morning “recorded volatility in the
voltages”, previous: “Rises and falls” prior to that zero and those
oscillations. That is why they are analyzing “not only that morning”,
but also the days prior to the blackout.

Aagesen explained that after these disconnections in these three
provinces, the synchronism with the European system was lost: the
interconnections with France jump, the Iberian Peninsula is isolated
from the rest of the continent and the “deregulation” occurs, that is,
the demand ceases to be fed. After disconnecting “the first step of
deregulation”, the frequency in the grid “continues to drop” and
“successive steps of deregulation” are activated in a short period of
time. At 12 hours, 33 minutes and 22 seconds “the sixth time step of
dredging” is activated and the system ends up collapsing to “peninsular
zero”.

The Vice-president explained that the inter-ministerial committee that
is analyzing the causes of the incident, which has already held six
meetings and has a group dedicated to the electricity system and another
for cybersecurity, is analyzing “millions of data with the best
equipment on behalf of the Administration”. He stated that the
collaboration of the sector\'s agents is being “full”. Information has
been requested from more than thirty generation control centers,
distributors and aggregations of large generation productions above
1,000 megawatts.

Translated with DeepL.com (free version)


(... continues on the link)

--
Cheers, Carlos.

 

[Carlos E.R.]

On 2025-05-14 19:19, john larkin wrote:

On Tue, 13 May 2025 22:28:23 +0200, \"Carlos E.R.\"
robin_listas@es.invalid> wrote:

On 2025-05-13 18:14, Bill Sloman wrote:
On 13/05/2025 11:48 pm, john larkin wrote:
On Tue, 13 May 2025 12:57:47 +0200, \"Carlos E.R.\"
robin_listas@es.invalid> wrote:


Nukes are great, but not if you tear them down.

Nukes are remarkably expensive, and depressingly inflexible. Radiation
damage to the structure means that you do have to tear them down after a
few decades of use, and the radioactive waste starts off very
radioactive, and the longer-lived isotopes have to be managed for a few
hundred thousand years.

And the investors building the stations do not consider the cost of
managing the waste for centuries. They leave that part to the
government. In Spain, we don\'t have any long term nuclear waste storage.
I think we rent storage in France, so the waste has to be transported
there. We have some storage at each station, a large water pool.

The best thing to do with used fuel rods is reprocess them into more
fuel.

Something that is expensive and not every country can do.

When that\'s not feasible, dig a deep hole and dump it in. Or drop
barrels of junk into an ocean subduction zone.

That\'s simply wrong.

It\'s irrational to store nuclear waste locally. Nuke policy is mostly
fear driven. And nukes are unpopular in some quarters by people who
really don\'t want us to have affordable, safe energy.

I have a very rational and studied fear of nuclear power.

--
Cheers, Carlos.

 

[Carlos E.R.]

On 2025-05-14 16:16, Glen Walpert wrote:

On Tue, 13 May 2025 07:50:36 -0700, Don Y wrote:

On 5/13/2025 6:26 AM, Glen Walpert wrote:
I don\'t think that using broadcast radio for real time mains grid
control is a good idea. It would be far too unreliable.

Point to point RF links have been in use in (mostly hard wired) grid
control SCADA (System Control And Data Acquisition) systems for at
least 30 years, which is when a former employer did some work on a
SCADA upgrade project for the Egyptian Electrical Authority. A search
on \'SCADA radio link\' will turn up several vendors.

And they used these to control instantaneous frequency and phase? Or,
just coarse data collection and /supervisory/ control?

SCADA is used to monitor and control the grid, where control is done in
real time by adjusting the set points for real and reactive power at all
controlled power sources. A small percentage of sources being
inaccessible degrades control by an insignificant amount.

Real power is regulated by the prime mover governors, which must be
operated in droop mode in order to share the load (the speed set point is
reduced with increasing load). The grid Hz/Gw figure which has been
mentioned is not directly related to generator inertia, where
insignificant energy is stored, it is the aggregate droop setting of the
prime mover governors feeding the grid. After speed/frequency shift (the
governors only measure shaft speed) due to a load change the grid control
center adjusts the governor set points to bring the frequency back to
normal.

Voltage regulation is entirely separate and is done by setting the
reactive power output of sources, again by adjusting set points in real
time over SCADA (or one of the other approved standard comm protocols).
This is a bit complex for a quick explanation but is described in detail
in any decent text covering synchronous generator control.

Voltage regulation is more likely to be a stability issue than frequency.
If you take two widely separated generators or sets of locally paralleled
generators at two power plants which are optimally tuned for stand alone
operation and connect them with a long transmission line, voltage will
begin to oscillate due to the time delay in locally detecting changes in
the other plants output. Detuning the regulators to achieve stability
results in inadequate response to load changes - thus central control of
both plants over SCADA.

Large generator voltage response time is limited by the L/R time constant,
which will be in the 10\'s of seconds, over a minute for some large multi-
pole hydroelectric generators. Inverters can respond much faster, with
potentially worse stability issues, and dividing power sources into many
small units does not make stability any easier, you still can\'t set
optimal tuning parameters for widely separated groups of sources which
will be both stable and fast, central control of some percentage of source
set points is required. This problem and it\'s solution is well understood
and the current generation of inverters are designed to allow remote
control of set points.

In the US more than 2/3 of all solar power is utility owned 10 MW or
larger and all of this is under central grid operator control, so no
stability issues there.

More intermittent power sources need more batteries, which are being
deployed by utilities as fast as they can be manufactured, being far
cheaper then peaking gas turbines, the most expensive of power sources.

https://www.tdworld.com/distributed-energy-resources/energy-storage/news/
55287560/us-energy-storage-industry-commits-100-billion-investment-in-
american-made-grid-batteries

Wouldn\'t it be easier to have the entire distribution network using DC?

just saying with a glass of wine in my hand

--
Cheers, Carlos.

 

[Joe Gwinn]

On Wed, 14 May 2025 21:07:21 +0200, \"Carlos E.R.\"
<robin_listas@es.invalid> wrote:

On 2025-05-10 18:46, Bill Sloman wrote:
One of my LinkedIn contacts - an IEEE contact in this case - posted some
new data on LinkedIn, from a \"Simon Gallagher, Managing Director at UK
Networks Services | CEng | FIET | FEI | MBA \"


Today the ministry said that they have ruled out a hacking of the REE,
but not in other places. And that it originated in Granada, Badajoz and
Sevilla (loss of generation).

Spanish:

https://www.eldiario.es/economia/aagesen-avanza-desconexiones-generacion-apagon-empezaron-granada-badajoz-sevilla_1_12297171.html

Aagesen says that the generation disconnections before the blackout
began in Granada, Badajoz and Seville.

They began with a substation in Granada and then occurred in
Badajoz and Seville; the vice-president speaks of ‘overvoltage’
problems, rules out a cyber-attack on Red Eléctrica and stresses that
‘hypotheses have already been ruled out’: it was not a problem of
coverage, reserve ‘or the size of the networks’.

The Third Vice-President and Minister for Ecological Transition, Sara
Aagesen, announced this Wednesday in the Congress of Deputies that the
generation losses prior to the historic blackout on 28 April ‘began in
Granada, Badajoz and Seville’. Aagesen, who confirmed that a
cyber-attack on Red Eléctrica has been ruled out, spoke of problems of
‘overvoltage’ in the system and explained that they are analysing
whether the oscillations detected in Europe half an hour before the cut
were related to the incident.

In an appearance in the plenary session to explain the crisis, the
vice-president explained that, after ‘at least two periods of
oscillations’ in the 30 minutes prior to the blackout, which were
detected in the peninsular and European system, with “low” demand at
that time, there were ‘three losses’ of generation: the first, ‘in a
substation in Granada’ at 12 hours, 32 minutes and 57 seconds; 19
seconds later, another substation in Badajoz was disconnected; and 20.3
seconds later, another in Seville. ‘The sum of these three events’
accumulated a loss of just over 2.2 gigawatts ‘in 20 seconds’.

The committee investigating the blackout is analyzing “disconnections
that may be due to overvoltage as a triggering element of the cascading
drop” that came just after. The control systems of the different
operators reflect that that morning “recorded volatility in the
voltages”, previous: “Rises and falls” prior to that zero and those
oscillations. That is why they are analyzing “not only that morning”,
but also the days prior to the blackout.

Aagesen explained that after these disconnections in these three
provinces, the synchronism with the European system was lost: the
interconnections with France jump, the Iberian Peninsula is isolated
from the rest of the continent and the “deregulation” occurs, that is,
the demand ceases to be fed. After disconnecting “the first step of
deregulation”, the frequency in the grid “continues to drop” and
“successive steps of deregulation” are activated in a short period of
time. At 12 hours, 33 minutes and 22 seconds “the sixth time step of
dredging” is activated and the system ends up collapsing to “peninsular
zero”.

The Vice-president explained that the inter-ministerial committee that
is analyzing the causes of the incident, which has already held six
meetings and has a group dedicated to the electricity system and another
for cybersecurity, is analyzing “millions of data with the best
equipment on behalf of the Administration”. He stated that the
collaboration of the sector\'s agents is being “full”. Information has
been requested from more than thirty generation control centers,
distributors and aggregations of large generation productions above
1,000 megawatts.

Translated with DeepL.com (free version)


(... continues on the link)

The Times of London published an article today:

..<https://www.thetimes.com/world/europe/article/blackout-risk-was-highlighted-two-years-before-spains-grid-went-down-lzvxdxvzf>

Joe

 

[john larkin]

On Wed, 14 May 2025 21:10:06 +0200, \"Carlos E.R.\"
<robin_listas@es.invalid> wrote:

On 2025-05-14 19:19, john larkin wrote:
On Tue, 13 May 2025 22:28:23 +0200, \"Carlos E.R.\"
robin_listas@es.invalid> wrote:

On 2025-05-13 18:14, Bill Sloman wrote:
On 13/05/2025 11:48 pm, john larkin wrote:
On Tue, 13 May 2025 12:57:47 +0200, \"Carlos E.R.\"
robin_listas@es.invalid> wrote:


Nukes are great, but not if you tear them down.

Nukes are remarkably expensive, and depressingly inflexible. Radiation
damage to the structure means that you do have to tear them down after a
few decades of use, and the radioactive waste starts off very
radioactive, and the longer-lived isotopes have to be managed for a few
hundred thousand years.

And the investors building the stations do not consider the cost of
managing the waste for centuries. They leave that part to the
government. In Spain, we don\'t have any long term nuclear waste storage.
I think we rent storage in France, so the waste has to be transported
there. We have some storage at each station, a large water pool.

The best thing to do with used fuel rods is reprocess them into more
fuel.

Something that is expensive and not every country can do.

A couple of very remote places in the world could do that. And we\'d
get lots of fun isotopes too. Can\'t leave hot rods in a zillion pools
forever.

When that\'s not feasible, dig a deep hole and dump it in. Or drop
barrels of junk into an ocean subduction zone.

That\'s simply wrong.

It\'s irrational to store nuclear waste locally. Nuke policy is mostly
fear driven. And nukes are unpopular in some quarters by people who
really don\'t want us to have affordable, safe energy.

I have a very rational and studied fear of nuclear power.

Why? It\'s very safe when done carefully.

The little modular reactors sound cool.

 

[Don Y]

On 5/14/2025 7:16 AM, Glen Walpert wrote:

On Tue, 13 May 2025 07:50:36 -0700, Don Y wrote:

On 5/13/2025 6:26 AM, Glen Walpert wrote:
I don\'t think that using broadcast radio for real time mains grid
control is a good idea. It would be far too unreliable.

Point to point RF links have been in use in (mostly hard wired) grid
control SCADA (System Control And Data Acquisition) systems for at
least 30 years, which is when a former employer did some work on a
SCADA upgrade project for the Egyptian Electrical Authority. A search
on \'SCADA radio link\' will turn up several vendors.

And they used these to control instantaneous frequency and phase? Or,
just coarse data collection and /supervisory/ control?

SCADA is used to monitor and control the grid, where control is done in
real time by adjusting the set points for real and reactive power at all
controlled power sources. A small percentage of sources being
inaccessible degrades control by an insignificant amount.

\"Real-time\" means different things to different applications.

I took Theo\'s upthread suggestion to mean broadcasting a *reference*
that all genertors would track -- instead of using the actual power line,
itself. I.e., the spain event could have been avoided if such a broadcast
reference were used by each generator DISREGARDING THE ACTUAL POWER SIGNAL.

I.e., a zero-crossing should occur.... NOW. And, NOW. And NOW. Even
if what the generator is OBSERVING seems to differ.

SCADA systems tend to operate at higher levels than the REAL real-time
control AT the field.

E.g., a tablet press produces tablets at ~200Hz. Controlling the details
of the actual process isn\'t going to happen at the far end of an RF link;
there\'s too much latency and not enough determinism.

However, you could tell the press to change it\'s operating conditions
\"when it can get around to it\" from a supervisory/control station
on the other side of the planet. Relying on the *local* RT controls
to ensure all of the product made while those status and control
messages are in flight are actually made properly.

Like counting on the generator\'s local controls to keep it producing power
under the previously established settings based on LOCAL observations...
while its status and control messages are on the wing.

 

[Phil Hobbs]

On 2025-05-14 17:37, john larkin wrote:

On Wed, 14 May 2025 21:10:06 +0200, \"Carlos E.R.\"
robin_listas@es.invalid> wrote:

On 2025-05-14 19:19, john larkin wrote:
On Tue, 13 May 2025 22:28:23 +0200, \"Carlos E.R.\"
robin_listas@es.invalid> wrote:

On 2025-05-13 18:14, Bill Sloman wrote:
On 13/05/2025 11:48 pm, john larkin wrote:
On Tue, 13 May 2025 12:57:47 +0200, \"Carlos E.R.\"
robin_listas@es.invalid> wrote:


Nukes are great, but not if you tear them down.

Nukes are remarkably expensive, and depressingly inflexible. Radiation
damage to the structure means that you do have to tear them down after a
few decades of use, and the radioactive waste starts off very
radioactive, and the longer-lived isotopes have to be managed for a few
hundred thousand years.

And the investors building the stations do not consider the cost of
managing the waste for centuries. They leave that part to the
government. In Spain, we don\'t have any long term nuclear waste storage.
I think we rent storage in France, so the waste has to be transported
there. We have some storage at each station, a large water pool.

The best thing to do with used fuel rods is reprocess them into more
fuel.

Something that is expensive and not every country can do.

A couple of very remote places in the world could do that. And we\'d
get lots of fun isotopes too. Can\'t leave hot rods in a zillion pools
forever.


When that\'s not feasible, dig a deep hole and dump it in. Or drop
barrels of junk into an ocean subduction zone.

That\'s simply wrong.

It\'s irrational to store nuclear waste locally. Nuke policy is mostly
fear driven. And nukes are unpopular in some quarters by people who
really don\'t want us to have affordable, safe energy.

I have a very rational and studied fear of nuclear power.

Why? It\'s very safe when done carefully.

The little modular reactors sound cool.

Putting used nuclear fuel someplace deepish underground is important.
While a nuclear war would be very very bad, surface storage makes it
much, much worse.

The Chernobyl disaster released about 3.5% of the core inventory of one
reactor out of four.(*)

One Hiroshima-size bomb on top of a comparable large nuke plant could
release all the inventory in all four cores, which would be about
4/0.035 ~ 114 times worse than Chernobyl.

If the site included extensive spent-fuel pools, the total would be
correspondingly larger--maybe 500 Chernobyls, maybe more. And that\'s
just one installation.

Not a bad score for one small bomb--there are lots bigger ones.

Cheers

Phil Hobbs

(*)
https://www.oecd-nea.org/jcms/pl_28292/chernobyl-chapter-ii-the-release-dispersion-deposition-and-behaviour-of-radionuclides

--
Dr Philip C D Hobbs
Principal Consultant
ElectroOptical Innovations LLC / Hobbs ElectroOptics
Optics, Electro-optics, Photonics, Analog Electronics
Briarcliff Manor NY 10510

http://electrooptical.net
http://hobbs-eo.com

 

[Carlos E.R.]

On 2025-05-14 22:45, Joe Gwinn wrote:

On Wed, 14 May 2025 21:07:21 +0200, \"Carlos E.R.\"
robin_listas@es.invalid> wrote:

On 2025-05-10 18:46, Bill Sloman wrote:
One of my LinkedIn contacts - an IEEE contact in this case - posted some
new data on LinkedIn, from a \"Simon Gallagher, Managing Director at UK
Networks Services | CEng | FIET | FEI | MBA \"


Today the ministry said that they have ruled out a hacking of the REE,
but not in other places. And that it originated in Granada, Badajoz and
Sevilla (loss of generation).

Spanish:

https://www.eldiario.es/economia/aagesen-avanza-desconexiones-generacion-apagon-empezaron-granada-badajoz-sevilla_1_12297171.html

....

(... continues on the link)

The Times of London published an article today:

.<https://www.thetimes.com/world/europe/article/blackout-risk-was-highlighted-two-years-before-spains-grid-went-down-lzvxdxvzf

pay wall.

Disabling javascript allows reading 4 paragraphs.


Anyway, government denies that a risk of total blackout had been
highlighted on any report.

--
Cheers, Carlos.

 

[Bill Sloman]

On 15/05/2025 5:14 am, Carlos E.R. wrote:

On 2025-05-14 16:16, Glen Walpert wrote:
On Tue, 13 May 2025 07:50:36 -0700, Don Y wrote:

On 5/13/2025 6:26 AM, Glen Walpert wrote:
I don\'t think that using broadcast radio for real time mains grid
control is a good idea. It would be far too unreliable.

Point to point RF links have been in use in (mostly hard wired) grid
control SCADA (System Control And Data Acquisition) systems for at
least 30 years, which is when a former employer did some work on a
SCADA upgrade project for the Egyptian Electrical Authority.  A search
on \'SCADA radio link\' will turn up several vendors.

And they used these to control instantaneous frequency and phase?  Or,
just coarse data collection and /supervisory/ control?

SCADA is used to monitor and control the grid, where control is done in
real time by adjusting the set points for real and reactive power at all
controlled power sources.  A small percentage of sources being
inaccessible degrades control by an insignificant amount.

Real power is regulated by the prime mover governors, which must be
operated in droop mode in order to share the load (the speed set point is
reduced with increasing load).  The grid Hz/Gw figure which has been
mentioned is not directly related to generator inertia, where
insignificant energy is stored, it is the aggregate droop setting of the
prime mover governors feeding the grid.  After speed/frequency shift (the
governors only measure shaft speed) due to a load change the grid control
center adjusts the governor set points to bring the frequency back to
normal.

Voltage regulation is entirely separate and is done by setting the
reactive power output of sources, again by adjusting set points in real
time over SCADA (or one of the other approved standard comm protocols).
This is a bit complex for a quick explanation but is described in detail
in any decent text covering synchronous generator control.

Voltage regulation is more likely to be a stability issue than frequency.
If you take two widely separated generators or sets of locally paralleled
generators at two power plants which are optimally tuned for stand alone
operation and connect them with a long transmission line, voltage will
begin to oscillate due to the time delay in locally detecting changes in
the other plants output.  Detuning the regulators to achieve stability
results in inadequate response to load changes - thus central control of
both plants over SCADA.

Large generator voltage response time is limited by the L/R time
constant,
which will be in the 10\'s of seconds, over a minute for some large multi-
pole hydroelectric generators.  Inverters can respond much faster, with
potentially worse stability issues, and dividing power sources into many
small units does not make stability any easier, you still can\'t set
optimal tuning parameters for widely separated groups of sources which
will be both stable and fast, central control of some percentage of
source
set points is required.  This problem and it\'s solution is well
understood
and the current generation of inverters are designed to allow remote
control of set points.

In the US more than 2/3 of all solar power is utility owned 10 MW or
larger and all of this is under central grid operator control, so no
stability issues there.

More intermittent power sources need more batteries, which are being
deployed by utilities as fast as they can be manufactured, being far
cheaper then peaking gas turbines, the most expensive of power sources.

https://www.tdworld.com/distributed-energy-resources/energy-storage/news/
55287560/us-energy-storage-industry-commits-100-billion-investment-in-
american-made-grid-batteries

Wouldn\'t it be easier to have the entire distribution network using DC?

just saying with a glass of wine in my hand

That\'s probably correct, but it wouldn\'t be cheaper. It\'s probably true
that taking DC down to the sub-station level could be cheaper, with
today\'s technology, if you were starting from scratch, but since that
kit is already there you would be throwing away a lot of big expensive
transformers from the next level up, and replacing them with a lot of
big, expensive - if less expensive - inverters. It would take a lot of
capital investment to make the switch, and the people who operate the
grid are adminstrators rather than entrepreneurs.

--
Bill Sloman, Sydney

 

[Bill Sloman]

On 15/05/2025 3:19 am, john larkin wrote:

On Tue, 13 May 2025 22:28:23 +0200, \"Carlos E.R.\"
robin_listas@es.invalid> wrote:

On 2025-05-13 18:14, Bill Sloman wrote:
On 13/05/2025 11:48 pm, john larkin wrote:
On Tue, 13 May 2025 12:57:47 +0200, \"Carlos E.R.\"
robin_listas@es.invalid> wrote:


Nukes are great, but not if you tear them down.

Nukes are remarkably expensive, and depressingly inflexible. Radiation
damage to the structure means that you do have to tear them down after a
few decades of use, and the radioactive waste starts off very
radioactive, and the longer-lived isotopes have to be managed for a few
hundred thousand years.

And the investors building the stations do not consider the cost of
managing the waste for centuries. They leave that part to the
government. In Spain, we don\'t have any long term nuclear waste storage.
I think we rent storage in France, so the waste has to be transported
there. We have some storage at each station, a large water pool.

The best thing to do with used fuel rods is reprocess them into more
fuel.

That doesn\'t do anything about the fission products which are a bunch of
isotopes of about half the atomic weight of uranium. Some of them have
short half-lives, and are very radioactive and some of them have longer
half-lives and have to be managed for longer periods, out to about a few
hundred thousand years

When that\'s not feasible, dig a deep hole and dump it in. Or drop
barrels of junk into an ocean subduction zone.

Over a hundred thousands years or so deep holes can\'t be relied on to
stay buried. Subduction zones are - by definition - geologically
unstable, and there\'s no guarantee that your chosen target will keep on
subducting.

https://www.csiro.au/en/news/all/articles/2023/february/radioactive-waste

talks about a way of treating nuclear waste that concentrates it and
makes it insoluble. One of the guys who worked on it - Lou Vance - was
an acquaintance of mine when we both undergraduates. He died recently,
and the process has been around for decades now, but nobody uses it.
Somebody in the UK is apparently running tests on it, but
not-in-my-back-yard is international.

It\'s irrational to store nuclear waste locally. Nuke policy is mostly
fear driven. And nukes are unpopular in some quarters by people who
really don\'t want us to have affordable, safe energy.

Nuclear power is neither cheap nor safe. Nuclear policy is pretty much
driven by people who want nuclear weapons and nuclear powered
submarines. The US has nuclear-powered aircraft carriers, but they
wouldn\'t last long in a modern war. U-235-fuelled nuclear reactors are a
source of plutonium, and any electric power they generate is bonus.

The absence of thorium reactors is a bit of a give-away.

--
Bill Sloman, Sydney

 

[Bill Sloman]

On 15/05/2025 7:37 am, john larkin wrote:

On Wed, 14 May 2025 21:10:06 +0200, \"Carlos E.R.\"
robin_listas@es.invalid> wrote:

On 2025-05-14 19:19, john larkin wrote:
On Tue, 13 May 2025 22:28:23 +0200, \"Carlos E.R.\"
robin_listas@es.invalid> wrote:

On 2025-05-13 18:14, Bill Sloman wrote:
On 13/05/2025 11:48 pm, john larkin wrote:
On Tue, 13 May 2025 12:57:47 +0200, \"Carlos E.R.\"
robin_listas@es.invalid> wrote:


Nukes are great, but not if you tear them down.

Nukes are remarkably expensive, and depressingly inflexible. Radiation
damage to the structure means that you do have to tear them down after a
few decades of use, and the radioactive waste starts off very
radioactive, and the longer-lived isotopes have to be managed for a few
hundred thousand years.

And the investors building the stations do not consider the cost of
managing the waste for centuries. They leave that part to the
government. In Spain, we don\'t have any long term nuclear waste storage.
I think we rent storage in France, so the waste has to be transported
there. We have some storage at each station, a large water pool.

The best thing to do with used fuel rods is reprocess them into more
fuel.

Something that is expensive and not every country can do.

A couple of very remote places in the world could do that. And we\'d
get lots of fun isotopes too. Can\'t leave hot rods in a zillion pools
forever.

Nobody does. Nuclear reactors are a useful source of medically useful
isotope - Australia has just one for that job, though it is also
exploited as a neutron source. I got interviewed for a job to upgrade
their neutron diffraction system - they\'d bough the original from France
thirty years ago. I didn\'t get the job, which was a bit of a relief. In
the 1980\'s I worked on a French shaped beam electron beam
microfabricator, and hadn\'t been impressed by the engineering.

When that\'s not feasible, dig a deep hole and dump it in. Or drop
barrels of junk into an ocean subduction zone.

That\'s simply wrong.

It\'s irrational to store nuclear waste locally. Nuke policy is mostly
fear driven. And nukes are unpopular in some quarters by people who
really don\'t want us to have affordable, safe energy.

I have a very rational and studied fear of nuclear power.

Why? It\'s very safe when done carefully.

Except when something unexpected goes wrong, as it did at Fukushima

https://en.wikipedia.org/wiki/Fukushima_nuclear_accident

> The little modular reactors sound cool.

The US nuclear submarines and aircraft carriers have relied on them for
decades. It\'s odd that there\'s never been a civilian version. \"Sounding
cool\" doesn\'t get you through a design review.

The fact that those reactors rely on much more heavily enriched
(weapons=grade) uranium that civil nuclear reactors may come into it.

--
Bill Sloman, Sydney

 

[Martin Brown]

On 15/05/2025 01:20, Carlos E.R. wrote:

On 2025-05-14 22:45, Joe Gwinn wrote:
On Wed, 14 May 2025 21:07:21 +0200, \"Carlos E.R.\"
robin_listas@es.invalid> wrote:

On 2025-05-10 18:46, Bill Sloman wrote:
One of my LinkedIn contacts - an IEEE contact in this case - posted
some
new data on LinkedIn, from a \"Simon Gallagher, Managing Director at UK
Networks Services | CEng | FIET | FEI | MBA \"


Today the ministry said that they have ruled out a hacking of the REE,
but not in other places. And that it originated in Granada, Badajoz and
Sevilla (loss of generation).

Spanish:

https://www.eldiario.es/economia/aagesen-avanza-desconexiones-generacion-apagon-empezaron-granada-badajoz-sevilla_1_12297171.html

...

(... continues on the link)

The Times of London published an article today:

.<https://www.thetimes.com/world/europe/article/blackout-risk-was-highlighted-two-years-before-spains-grid-went-down-lzvxdxvzf

pay wall.

Disabling javascript allows reading 4 paragraphs.


Anyway, government denies that a risk of total blackout had been
highlighted on any report.

You trust your government *not* to lie about such things? How quaint!!

It conflicts with this popular media source and other tech sources:

https://www.surinenglish.com/spain/the-government-known-since-january-from-red-20250506082807-nt.html

Only the date when they were warned varies with the source.

--
Martin Brown