Cost analysis using hybrid gazelle and seagull optimization for home energy management system

Conventional electricity is more dependable, cost-effective, and robust, but it cannot meet the demands of the modern world. As a result, numerous strategies have been created to meet these demands, making the smart microgrid preferable to the conventional electricity grid. A home energy management system (HEMS) is one of the key elements of a power system that improves the energy performance of an electricity supply in a populated area. This paper forecasted electricity generated from renewable and non-renewable resources using the bidirectional long short-term memory (BLSTM) and the capsule network (capsnet). The hybrid gazelle and seagull optimization algorithm (HGSOA) reduces the peak power between the peak and off-peak time. The implementation process is performed on the MATLAB platform to evaluate the accuracy of the HEMS results. As a result, the proposed method has reduced the error, and the peak-to-average ratio is 1.21. When compared with the machine learning method, the proposed method reduced the error to 17.82% and 19.78% with deep learning methods.