Optimal energy storage system management in an uncertain smartgrid

Abstract

The proliferation of RESs within the residential sector, while a significant step towards a more sustainable energy landscape, presents unique challenges for power system operators. The intermittent nature of renewable generation, primarily solar and wind, can introduce substantial variability and uncertainty into the grid. Additionally, rapid fluctuations in renewable generation can strain the grid infrastructure, requiring investments in advanced grid management systems and energy storage solutions to maintain system stability and reliability. This paper proposed a comprehensive framework to optimize the operation and profitability of a microgrid. By leveraging advanced forecasting techniques and a hybrid cascaded neural network architecture, the model accurately predicts day-ahead net load and electricity prices. The proposed VMD-MIIG-CNN-GRU-BiLSTM algorithm achieves a mean absolute percentage error (MAPE) of approximately 6 % for net load forecasting and 7 % for electricity price forecasting, demonstrating its effectiveness in capturing the inherent complexities of these variables. Furthermore, the paper investigates the impact of ESS on microgrid profitability. The results indicate that incorporating an optimally sized ESS can enhance microgrid revenue by $1870, highlighting the economic benefits of energy storage in mitigating the challenges posed by renewable energy integration.