Hybrid-integer algorithm for a multi-objective optimal home energy management system

Most of the energy produced in the world is consumed by commercial and residential buildings.With the growth in the global economy and world demographics,this energy demand has become increasingly important.This has led to higher unit electricity prices,frequent stresses on the main electricity grid and carbon emissions due to inefficient energy management.This paper presents an energy-consumption management system based on time-shifting of loads according to the dynamic day-ahead electricity pricing.This simultaneously reduces the electricity bill and the peaks,while maintaining user comfort in terms of the operating waiting time of appliances.The proposed optimization problem is formulated mathematically in terms of multi-objective integer non-linear programming,which involves constraints and consumer preferences.For optimal scheduling,the management problem is solved using the hybridization of the particle swarm optimization algorithm and the branch-and-bound algorithm.Two techniques are proposed to manage the trade-off between the conflicting objectives.The first technique is the Pareto-optimal solutions classification using supervised learning methods.The second technique is called the lexicographic method.The simulations were performed based on residential building energy consumption,time-of-use pricing(TOU)and critical peak pricing(CPP).The algorithms were implemented in Python.The results of the current work show that the proposed approach is effective and can reduce the electricity bill and the peak-to-average ratio(PAR)by 28% and 49.32%,respectively,for the TOU tariff rate,and 48.91% and 47.87% for the CPP tariff rate by taking into account the consumer’s comfort level.

Day-ahead seasonal solar radiation prediction,combining VMD and STACK algorithms

This article proposes a method for accurately predicting solar irradiance over a 24-hour horizon to forecast photovoltaic energy generation in a positive-energy building.In order to make this prediction,the input data are divided into seasons and preprocessed using the variational mode decomposition(seasonal-VMD)method.The VMD method is used for extracting high-bandwidth features from the input data,decomposing them into a finite number of smooth modes and focusing on specific frequency ranges.Hence,the accuracy of signal extraction using the VMD method can be improved by selecting particular parameters judiciously,which impacts the smoothing and frequency concentration of the extracted signal.In this regard,the salp swarm algorithm(SSA)is employed to identify the optimal VMD parameters that can be used to enhance extraction accuracy.In addition,the obtained residual between the observed solar irradiation data and their decomposed modes is treated to enhance the prediction process.A stacking algorithm(STACK)is used to predict the following 24-hour solar irradiance modes and the residual,which are finally summed to reconstruct the desired signal.The performances of the proposed prediction method are evaluated using two quantitative evaluation indices:the normalized root mean square percentage error(NRMSPE)and normalized mean absolute percentage error(NMAPE).The proposed model is trained on data collected for three years in Rabat(2019–22).The performance of the proposed model is evaluated by predicting the 24-hour solar irradiance for a different season.The proposed approach seasonal-VMD-STACK is compared with two other methods in the case of using VMD-based STACK without season partition and STACK method only.Moreover,the proposed method has exhibited stability and proven good results with an NRMSPE of 3.87%and an NMAPE of 1.58%for cloudy days during the test phase.The results demonstrate that residual preprocessing,seasonal input data partition and appropriate selection of VMD parameters improve the performance and accuracy of the prediction.