Profitability of competing flexibility options in renewable-dominated energy markets: Combining agent-based and machine learning approaches

Rising price spreads on the electricity market have sparked the interest of investors in flexibility options. German transmission system operators received over 226 GW of battery storage connection requests in 2024. However, some uncertainty remains regarding the impact of large-scale storage deployment on electricity markets and their economic performance under competition. To address this, we use the open agent-based electricity market model AMIRIS, calibrated to a 2030 scenario based on the Ariadne report. We extend AMIRIS with a state-of-the-art machine-learning-based routine to provide agents with electricity price forecasts during runtime. These forecasts enable AMIRIS to model competing flexibility options. We evaluate the forecast accuracy and analyze its influence on the operation and profitability of competing flexibility options. Our results show that imperfect forecasts created by, e.g., machine learning algorithms, may reduce the revenues of flexibility options and that operational strategies significantly affect the revenues. Given sufficiently accurate forecasts, “risk-affine” strategies yield higher revenues, but also yield more full charge cycles than “risk-averse” strategies. At the system level, we identify a profitability plateau for homogeneous storage systems with installed power between 4 to 8 GW and total capacity of 32 GWh. Depending on installation costs, annual return on investment can reach around 20% through day-ahead market arbitrage. While heterogeneous storage technologies initially maintain their revenue shares, individual profitability declines significantly beyond critical capacity levels. These findings suggest that the volume of current German connection requests may exceed economically sustainable deployment levels under current market structures. Future research can build on our open modelling tool chain to integrate additional revenue streams, such as cross-market participation or system services remuneration.