Learning Spatiotemporal Dynamics in Wholesale Energy Markets with Dynamic Mode Decomposition

Abstract

Energy markets facilitate the balancing of electricity generation (supply) and demand while ensuring non-discriminatory access. Understanding energy market dynamics is essential to improving grid efficiency and resilience and optimizing the development of new energy conversion and storage technologies. Accurate energy price forecasts are essential for many energy storage technologies to be profitable from price arbitrage. In this paper, we apply the novel spatial-temporal dimensionality reduction method of Dynamic Mode Decomposition (DMD) to forecast 6587 locational marginal prices in the California Independent System Operator (CAISO) on the Day-Ahead Market (DAM). DMD is a promising equation-free modeling technique in systems with inherent periodic tendencies in time such as financial markets and fluid dynamics. Yet we show, for the first time, that DMD cannot reliably forecast day-ahead energy prices due to the so-called standing wave problem. Instead, we find Augmented DMD (ADMD) overcomes these limitations is a fast and accurate price forecaster. We benchmark DMD, ADMD, and backcasting forecasting methods for optimal price arbitrage with an energy storage system. We find, using ADMD, a market-connected energy storage system can capture up to 92% of allowable revenues in rolling horizon simulations. Lastly, we show ADMD is up to 1000-times faster than time-series forecasting methods (i.e., ARIMA) which requires orders of magnitude less data than deep/machine learning techniques.