Algorithms for the control and optimisation of assets including batteries can be an energy trader's best friend - nearly all of the time. Aaron Lally, managing partner at UK-based clean tech trading house, VEST Energy, explains why it's good to know when to switch from automation to human-controlled trading.
At my company, VEST, we believe in price algorithms and full trading automation.
They solve the asset optimisation problem in 90% of scenarios under normal market conditions. But what happens when an optimiser is reliant on algorithms in the 10% of tail scenarios - when our usual expectations are turned upside down and revenue generation could be at its highest?
Well, we are currently living through one of those tail scenarios and in all honesty it has not been great for trading algorithms with price models falling over due to unpredictable demand.
This has made wholesale market trading tougher and has led National Grid to reduce the dispatch of assets such as batteries in the Balancing Mechanism (BM). Revenues have remained substantial however in both existing and new ancillary service markets where the use of algorithms is more limited.
Does this happen in all tail events? What about tail events which increase the profit potential of assets? In March 2018 we saw the ‘Beast from the East’ weather event push short term power and gas prices significantly higher.
I was proprietary trading short term power markets using advanced artificial intelligence (A.I.) algorithms during this period. Our algorithms were instructing us to sell all settlement periods that week as prices moved substantially higher.
Thankfully we had experienced traders in place to limit any losses.
After the first day of inaccurate forecasts we stopped trading using all algorithms but continued human trading with success (although at reduced volumes due to market volatility). We kept running our algorithms as part of our testing and the algorithms could not cope with the market volatility.
Humans can (sometimes) adjust faster
After investigation we were able to determine that the algorithms had particular biases due to low price volatility in recent years and the dataset for volatility events such as March 2018 being so limited. The algorithms were unable to adjust to the prevailing market conditions. As we employed traders that had experienced this type of event previously - in March 2013 in particular - we were able to navigate through the ‘Beast from the East’ using human traders alone and reverted to algorithmic trading in late March 2018.
If we were solely using algorithms to trade assets during this period we would have missed the most volatile market environment in recent years.
Was it just our algorithms that failed? Did other systematic traders profit from this market volatility? In short, no. Human traders prevailed across the market with traders using algorithms with no override in both the short- and long-term power markets taking heavy losses.
It is easy to read this blog and point to the algorithmic trading segment of the power market maturing since 2018. It definitely has but in truth we will only see how algorithms perform when we move back into a volatile market regime. As in all trading markets, when this happens, there will be winners and losers.
Over the next few years VEST will be trading electricity markets with strong price prediction algorithms and extensive human trading experience in place to diversify our trading service when required. We recommend asset owners are prepared in a similar manner using traders and optimisers that employ multiple strategies to maximise the value of their assets as volatility returns.
Cover image: the so-called Beast from the East brought in unexpectedly freezing weather to Britain in March 2018, sending power and gas prices upwards in the short term. Credit: Flickr user Sean Truscott photography.
Stay up to date with the latest news, analysis and opinions. Sign up here to the Energy-Storage.news Newsletter.