The Integration of a Genetic Programming-Based Feature Optimizer With Fisher Criterion and Pattern Recognition Techniques to Non-Intrusive Load Monitoring for Load Identification

Identification of electricity energy consumption on individual household appliances used in a smart house is the first important step for making the use and conservation of electricity energy more efficient. In the past, Non-Intrusive Load Monitoring (NILM) techniques, which are part of smart grid techniques realized to improve electricity energy usage efficiency, have been developed to identify individual appliances with avoiding installing many smart meters for appliances in a field. In this paper, a new NILM technique that integrates an efficient Genetic Programming (GP)-based feature optimizer with pattern recognition techniques is proposed to identify which appliance is being turned on or off. The proposed GP-based feature optimizer with Fisher criterion is used to generate a more efficient feature than original potential transient features extracted from captured transient response of household appliances through analysis of NILM. The new feature generated by GP is used by pattern recognition techniques as load identifiers for load identification. The load identifiers used and compared in this paper include k-Nearest-Neighbor Rule, Back-Propagation Artificial Neural Network, and Learning Vector Quantization. Experiments are conducted under different single-load and multiple-load operation circumstances at different actual experimental environments with small disturbances. As shown from the experimental results, the proposed is confirmed to be feasible and usable.