Deep learning based optimal energy management for photovoltaic and battery energy storage integrated home micro-grid system

• Published in: Scientific reports Vol. 12; no. 1; p. 15133
• Main Authors: Alam, Md. Morshed, Rahman, Md. Habibur, Ahmed, Md. Faisal, Chowdhury, Mostafa Zaman, Jang, Yeong Min
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 07-09-2022; Nature Publishing Group; Nature Portfolio
• Subjects: 639/166/4073; 639/166/987; Artificial intelligence; Deep learning; Electricity; Energy management; Energy storage; Humanities and Social Sciences; Long short-term memory; multidisciplinary; Peak demand; Photovoltaics; Prediction models; Renewable energy sources; Renewable resources; Science; Science (multidisciplinary); Sustainable yield
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-022-19147-y

The development of the advanced metering infrastructure (AMI) and the application of artificial intelligence (AI) enable electrical systems to actively engage in smart grid systems. Smart homes with energy storage systems (ESS) and renewable energy sources (RES)-known as home microgrids-have become a critical enabling technology for the smart grid. This article proposes a new model for the energy management system of a home microgrid integrated with a battery ESS (BESS). The proposed dynamic model integrates a deep learning (DL)-based predictive model, bidirectional long short-term memory (Bi-LSTM), with an optimization algorithm for optimal energy distribution and scheduling of a BESS-by determining the characteristics of distributed resources, BESS properties, and the user’s lifestyle. The aim is to minimize the per-day electricity cost charged by time-of-use (TOU) pricing while considering the day-basis peak demand penalty. The proposed system also considers the operational constraints of renewable resources, the BESS, and electrical appliances. The simulation results from realistic case studies demonstrate the validation and responsibility of the proposed system in reducing a household’s daily electricity cost.