Electricity Price Prediction for Energy Storage System Arbitrage: A Decision-Focused Approach

Abstract

Electricity price prediction plays a vital role in energy storage system (ESS) management. Current prediction models focus on reducing prediction errors but overlook their impact on downstream decision-making. So this paper proposes a decision-focused electricity price prediction approach for ESS arbitrage to bridge the gap from the downstream optimization model to the prediction model. The decision-focused approach aims at utilizing the downstream arbitrage model for training prediction models. It measures the difference between actual decisions under the predicted price and oracle decisions under the true price, i.e., decision error, by regret, transforms it into the tractable surrogate regret, and then derives the gradients to predicted price for training prediction models. Based on the prediction and decision errors, this paper proposes the hybrid loss and corresponding stochastic gradient descent learning method to learn prediction models for prediction and decision accuracy. The case study verifies that the proposed approach can efficiently bring more economic benefits and reduce decision errors by flattening the time distribution of prediction errors, compared to prediction models for only minimizing prediction errors.

The Value of Energy Storage in Facilitating Renewables: A Northeast Area Analysis

“…We note that most scenarios are similar, so we propose to leverage the KMEANS++ algorithm with SSE analysis to extract the typical scenarios for planning analysis with high efficiency. We leverage the above model to show the value of energy storage in facilitating renewables in the following (6):…”

“…So, energy storage, due to its advantages of flexibility, rapid response, and clean and non-polluting nature, is expected to play a crucial role in the future energy system [6].…”

Investment Decision for Long-Term Battery Energy Storage System Using Least Squares Monte Carlo

“…Future uncertain demand has been modeled using GBM, and studies have been conducted on the arbitrage of Vanadium Redox Batteries [21]. Nguyen analyzed energy arbitrage considering the congestion of transmission and distribution systems, and Sang examined the prediction of electricity prices to maximize ESS arbitrage [22,23]. A Monte Carlo simulation was used to mitigate uncertainty in revenue [24].…”

Safety-Aware Semi-End-to-End Coordinated Decision Model for Voltage Regulation in Active Distribution Network

“…This formulation may seem counter-intuitive, given that "perfect" prediction models would lead to optimal decision-making. However, the reality that all models do inherit errors illustrates that we should indeed emphasize a final decision-quality objective to determine the proper error trade-offs within a machine learning setting [28]- [30]. The objectives of the prediction and decisionmaking stages are not the same, and under the same prediction accuracy, the decision quality can be further improved.…”