Quantum Inspired Evolutionary Algorithm based on Day Ahead Market of the Polish Electricity Power Exchange

Abstract

The paper discusses the essence of the method and selected results of the quantum-inspired implementation of the so-called System Evolutionary Algorithm on the example of the neural model of the Day-Ahead Market of the Polish Electricity Exchange Market S.A. First, the appropriate Perceptron Artificial Neural Network was designed and implemented in the MATLAB and Simulink environment, in which the Day-Ahead Market model was taught. Then it was assumed that the obtained parameters of the neural model, i.e. weights and biases, are quantum-encoded numbers, the values of whichwere corrected by the quantum-inspired Evolutionary Algorithm. Finally, a hybrid model was obtained in the form of an Artificial Neural Network with weights and biases corrected by a quantum inspired Evolutionary Algorithm. As a result of the conducted research, the relative error improvement was obtained from the level for different hours of the day from -0.11% ÷ 0.12% to the level from 0.04% ÷ 0.05%, i.e. by an order of magnitude. Moreover, the improvement of the quantum-inspired evolutionary algorithm measured by the fitness metric formulated as MSE error was achieved from a value of 0.990366 to a value of 0.990375.