Home Energy Management System(HEMS) Based on Non-Intrusive Load Monitoring

Home Energy Management Systems (HEMS) can achieve objectives such as reducing household electricity costs and enhancing users comfort by monitoring the electricity consumption of various household loads and executing corresponding optimization strategies. In this work, we investigate a HEMS based on Non-Intrusive Load Monitoring (NILM). An autoencoder neural network model combined with the TOPSIS (Technique for Order Preference by Similarity to an Ideal Solution) evaluation method is utilized for load feature extraction and recognition. Genetic algorithms are employed for electricity consumption optimization, ultimately aiming to minimize user electricity costs.