vix.ing · top · new · best · stats · spec

Exploring market power using deep reinforcement learning for intelligent\n bidding strategies

2020/11/08 by Alexander Kell, Kell, Alexander J. M., Matthew Forshaw +3
Engineering · #Artificial Intelligence (cs.AI) #Computational Engineering #Electric Power System Optimization #FOS: Computer and information sciences #Finance #Optimal Power Flow Distribution #Smart Grid Energy Management #and Science (cs.CE)

paper · pdf · doi:10.48550/arxiv.2011.04079

openalex publication_date 2020/11/08 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28

Abstract

Decentralized electricity markets are often dominated by a small set of\ngenerator companies who control the majority of the capacity. In this paper, we\nexplore the effect of the total controlled electricity capacity by a single, or\ngroup, of generator companies can have on the average electricity price. We\ndemonstrate this through the use of ElecSim, a simulation of a country-wide\nenergy market. We develop a strategic agent, representing a generation company,\nwhich uses a deep deterministic policy gradient reinforcement learning\nalgorithm to bid in a uniform pricing electricity market. A uniform pricing\nmarket is one where all players are paid the highest accepted price. ElecSim is\nparameterized to the United Kingdom for the year 2018. This work can help\ninform policy on how to best regulate a market to ensure that the price of\nelectricity remains competitive.\n We find that capacity has an impact on the average electricity price in a\nsingle year. If any single generator company, or a collaborating group of\ngenerator companies, control more than \∼11 % of generation capacity\nand bid strategically, prices begin to increase by \∼25 %. The value of\n\∼25 % and \∼11 % may vary between market structures and countries.\nFor instance, different load profiles may favour a particular type of generator\nor a different distribution of generation capacity. Once the capacity\ncontrolled by a generator company, which bids strategically, is higher than\n\∼35 %, prices increase exponentially. We observe that the use of a\nmarket cap of approximately double the average market price has the effect of\nsignificantly decreasing this effect and maintaining a competitive market. A\nfair and competitive electricity market provides value to consumers and enables\na more competitive economy through the utilisation of electricity by both\nindustry and consumers.\n

Related