Measuring Peak Shaving Efficiency of an Energy Storage Device Under Load Uncertainty with Machine Learning-Based Forecasting Techniques

Energy storage systems enhance grid efficiency by mitigating peak demand and balancing generation variability. This work addresses the challenge of achieving optimal peak shaving without prior knowledge of the actual load profile. To this end, we introduce the Forecast-Integrated Shortest Path (FISP) framework, which integrates load forecasting with the shortest-path optimization algorithm to determine optimal generation and storage strategies under forecast uncertainty. A penalty-based metric is proposed to quantify the deviation between forecast-driven and ideal operation, providing a unified measure of forecast-to-optimization performance. The proposed approach is validated using real load data from the European Network of Transmission System Operators for Electricity (ENTSO-E) and evaluated with two forecasting techniques—Long Short-Term Memory (LSTM) networks and Autoregressive Moving Average (ARMA) models. The results show that LSTM-based forecasts yield substantially lower penalties than ARMA, demonstrating that accurate prediction combined with intelligent storage control can significantly enhance operational reliability and peak-shaving performance.