Fully-connected layers-embedded self-attention optimizer based on quantum-inspired and fuzzy logic for smart household energy management

Abstract

On the road to carbon neutrality, the solution to the power consumption optimization problem of thousands of households is an essential link. This work mainly constructs a mathematical model of a smart household energy management system (HEMS) considering the real-time users’ willingness. The work proposes a fully-connected layers-embedded self-attention optimizer (FCSAO) based on quantum and fuzzy logic for the HEMS models. The FCSAO is an optimization method accelerated by fully-connected layers-embedded self-attention networks (FCSANs), quantum-inspired logic, and fuzzy logic. In a conventional optimization algorithm iteration process, a generative adversarial network incorporating a self-attention mechanism is adopted to characterize the input-output relationship of the optimization problem, and a quantum universal gate is employed to train the deep network by dividing the dataset into four classes based on the output of the optimization problem. The trained deep network can accelerate the iterative process of traditional optimization algorithm. The smart HEMS divides the loads in the home into rigid loads, adjustable loads, and air conditioner loads. The smart HEMS model meets the goals of users to save electrical energy and reduce electricity price expenditure by the proposed FCSAO based on quantum-inspired and fuzzy logic. Besides, the smart HEMS model can effectively control the operation state of the air conditioner and give the optimal operation time of adjustable loads. Furthermore, with three different scenarios simulated in MATLAB, the optimized indoor temperature meets users’ willingness for temperature comfort level by the proposed FCSAO based on quantum-inspired and fuzzy logic with great expression capability; the proposed FCSAO saves 1.05 % electricity cost.