Electricity balancing is one of the main demanders of short-term flexibility. To improve its integration, the recent regulation of the European Union introduces a common standalone balancing energy market. It allows actors that have not participated or not been awarded in the preceding balancing capacity market to participate as voluntary bidders or ‘second-chance’ bidders. We investigate the effect of these changes on balancing market efficiency and on strategic behavior in particular, using a combination of agent-based modelling and reinforcement learning. This paper is the first to model agents' interdependent bidding strategies in the balancing capacity and energy markets with the help of two collaborative reinforcement learning algorithms. Results reveal considerable efficiency gains in the balancing energy market from the introduction of voluntary bids even in highly concentrated markets while offering a new value stream to providers of short-term flexibility. ‘Second-chance’ bidders further drive competition, reducing balancing energy costs. However, we warn that this design change is likely to shift some of the activation costs to the balancing capacity market where agents are prompted to bid more strategically in the view of lower profits from balancing energy. As it is unlikely that the balancing capacity market can be removed altogether, we recommend integrating European balancing capacity markets on par with balancing energy markets and easing prequalification requirements to ensure sufficient competition.

电力平衡是短期灵活性的主要要求之一。为了改善其一体化，欧盟最近的法规引入了一个共同的独立平衡能源市场。它允许未参与或未获得先前平衡能力市场中标的参与者作为自愿投标人或“二次机会”投标人参与。我们使用基于代理的建模和强化学习的组合来研究这些变化对平衡市场效率和战略行为的影响。本文是第一个借助两种协作强化学习算法对平衡容量和能源市场中代理的相互依赖的投标策略进行建模的论文。结果显示，即使在高度集中的市场中，引入自愿投标也能在平衡能源市场中获得可观的效率收益，同时为短期灵活性的供应商提供新的价值流。“第二次机会”投标者进一步推动竞争，降低平衡能源成本。但是，我们警告说，这种设计更改可能会将部分激活成本转移到平衡容量市场，在该市场中，鉴于平衡能源的利润较低，代理商会被提示更具战略性地出价。由于不太可能完全取消平衡容量市场，我们建议将欧洲平衡容量市场与平衡能源市场相结合，并放宽资格预审要求，以确保充分竞争。