Octopus Free events logic

[AndySmithers]

I'm not sure if I'm misunderstanding something - or just plain overthinking!
Up until now I've been on Agile and thus the free events have been pretty much irrelevant to me since the agile rates at those times have always been at least as good as free.
I've recently changed to Go and thus have set up the Free sessions sensors.
All works OK, at the free slot the import price is shown as 0p and thus Predbat eagerly charges the battery.
But, the "free" sessions are not really free, they are only free for any electricity you use over what you normally use in the last 10 days at that time.
Now, let's imagine a situation:
On Tuesday there's a free session from 14:00 to 15:00 and Predbat diligently pulls 10kWh to charge my battery.
Since I usually use zero then all of that 10kWh is "free" (once Octopus gets around to crediting it).
Now let's assume that the following Tuesday there is another "free" event from 14:00 to 15:00 again.
Predbat will again charge the battery (even discharging before hand to make maximum use of the free electricity).
But, this time your average use in the last 10 days in the 14:00-15:00 times slot is NOT zero, thus some of this "free" electricity will in fact be charged at the 32p peak rate.
Predbat doesn't know this.

But.. Predbat could access this information.
It knows all your load (and car) usage over the last many days from the HA database.
Could not Predbat use this information to calculate the real effective rate of the "free" slot and thus make more intelligent decisions as to whether it's worth charging the battery?

[gcoan]

But, this time your average use in the last 10 days in the 14:00-15:00 times slot is NOT zero, thus some of this "free" electricity will in fact be charged at the 32p peak rate.
Predbat doesn't know this.

No, you are incorrect.

See https://octopus.energy/free-electricity/

"How do you work out my normal use?

We'll look at your historical smart meter readings to work out your typical energy use at that time of day.
If the Session is on a weekday, we'll look at your half-hourly usage over the last 10 weekdays. If the Session is at the weekend, we'll look at your half-hourly usage at that time within the last 4 weekend days. We'll not include days where a Session took place in these calculations."

In terms of the concern you had, its not a concern.

In practice I find that most of the free electricity sessions occur when its pretty sunny and I'm already generating more than I can charge my batteries with, so I'm net exporting in those sessions and not getting much financial advantage. But if you have a higher home load or higher inverter charge rate than your solar generation then you can take some benefit.

It knows all your load (and car) usage over the last many days from the HA database.
Could not Predbat use this information to calculate the real effective rate of the "free" slot

In practice not really because Predbat can't know what other house load you are going to have running in the free electricity session and whether that is higher or lower than your historical average load.

[AndySmithers]

Ah, thanks. I had missed the highlighted bit.

[Nilogax]

I've noticed an issue with Octopus' calculation of the refund. On one recent session my car didn't charge but with battery charging etc I used almost 10kWh extra. The Octopus billing page shows that this was charged at the standard rate but the refund from octopus is based on the 7p rate so I've ended up paying for the extra "free" electricity I used. I'm currently "discussing" this with Octopus!

So it's worth checking to see if you've been affected in the same way.

[AndySmithers]

FWIW, I just checked my free energy usage on Sept. 11th and the refund they've given me is definitely based on the peak 32p rate. (I used about 3kWh extra and got 96p refund). So, their calculation does work - there must be some issue with your account. I dont see any way to see Octopus' calculation on their website or app, but having HA makes it easy for us to check this.

[Nilogax]

Thanks - useful info. So far they've basically confirmed that it did actually cost me more than their refund and that their calculations can go wrong sometimes. The have offered a rebate of the difference too but I'm wondering if other people are getting affected too.

My background is managing the data analytics team for a large and complex database so I know it isn't always straightforward to work this stuff out, but I also know that if my team was doing this and got a bug report from a customer we'd be all over it looking for a solution.