Market demand forecasting and resource scheduling for independent energy storage in the power grid based on deep learning integration
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Demand forecasting and resource scheduling face numerous challenges in the power grid. These include an abundance of data, an increasing number of factors impacting the demand profile, uncertainty surrounding the generation profile of distributed energy from renewable sources, and a lack of historical data. In this paper, we provide an innovative AI-based market-oriented energy storage approach that integrates grid service providers, energy storage facilities, and end users to maximise operational profit in the electricity market. Finding the optimal charging or discharging operation taking grid peak states, load demand, and battery status into account is the goal of this work, which employs deep learning based on Demand based Fish Swarm Optimisation and Long Short Term Memory (DFSO-LSTM). This study compares the performance of the current approach with that of the proposed method, focussing on the latter's 20-second execution time savings and 0.007 percent low MAPE. Based on the findings, the suggested approach optimises operational profit, boosts effective performance, and drastically reduces on-peak power.