Energy Storage Price Arbitrage via Opportunity Value Function Prediction

TL;DR

This paper introduces a neural network-based method for energy storage price arbitrage that predicts opportunity costs to optimize profits, outperforming existing methods with high transferability and low computational cost.

Contribution

The paper presents a novel approach combining supervised learning with dynamic programming to predict opportunity value functions for energy storage arbitrage.

Findings

Achieves 65% to 90% profit compared to perfect foresight.

Outperforms existing model-based and learning-based methods.

Model trained in one region transfers well to others.

Abstract

This paper proposes a novel energy storage price arbitrage algorithm combining supervised learning with dynamic programming. The proposed approach uses a neural network to directly predicts the opportunity cost at different energy storage state-of-charge levels, and then input the predicted opportunity cost into a model-based arbitrage control algorithm for optimal decisions. We generate the historical optimal opportunity value function using price data and a dynamic programming algorithm, then use it as the ground truth and historical price as predictors to train the opportunity value function prediction model. Our method achieves 65% to 90% profit compared to perfect foresight in case studies using different energy storage models and price data from New York State, which significantly outperforms existing model-based and learning-based methods. While guaranteeing high profitability, the algorithm is also light-weighted and can be trained and implemented with minimal computational cost. Our results also show that the learned prediction model has excellent transferability. The prediction model trained using price data from one region also provides good arbitrage results when tested over other regions.