A hybrid non-dominated sorting genetic algorithm for a multi-objective demand-side management problem in a smart building

Abstract

One of the most significant challenges facing optimization models for the demand-side management (DSM) is obtaining feasible solutions in a shorter time. In this paper, the DSM is formulated in a smart building as a linear constrained multi-objective optimization model to schedule both electrical and thermal loads over one day. Two objectives are considered, energy cost and discomfort caused by allowing flexibility of loads within an acceptable comfort range. To solve this problem, an integrative matheuristic is proposed by combining a multi-objective evolutionary algorithm as a master level with an exact solver as a slave level. To cope with the non-triviality of feasible solutions representation and NP-hardness of our optimization model, in this approach discrete decision variables are encoded as partial chromosomes and the continuous decision variables are determined optimally by an exact solver. This matheuristic is relevant for dealing with the constraints of our optimization model. To validate the performance of our approach, a number of simulations are performed and compared with the goal programming under various scenarios of cold and hot weather conditions. It turns out that our approach outperforms the goal programming with respect to some comparison metrics including the hypervolume difference, epsilon indicator, number of the Pareto solutions found, and computational time metrics. 560 or other forms of financial incentives. For instance, in a smart building, the smart meter receives external price signal such as time of use pricing (ToU) which vary depending on three periods, off-peak, mid-peak and on-peak price periods, and then all connected energy devices are scheduled to give a better economic planning, but affecting consumer preferences, so that it might be operated at undesired periods. However, in such circumstances, considering a trade-off between the economic targets of the DSM and a convenient lifestyle is substantial. The automatic implementation of the DSM scheduling model in a smart building (B-DSM) is performed by using a home/building energy management system (HEMS/BEMS) and is becoming a challenging with respect to diversity of building appliances, targets and constraints to be optimized. Different B-DSM optimization models for the HEMS or BEMS have been established in the literature. For instance in [4], an appliance-scheduling is proposed taking into account a photovoltaic panel and a hybrid electric vehicle (PHEV). A dynamic multi-swarm with learning strategy is applied to solve the proposed model with the objective of reducing the weighted sum of the electricity payments, consumer's dissatisfaction and carbon dioxide emissions. In [5] the B-DSM with household appliances and a battery is proposed. The authors minimize the electricity cost and the discomfort level. The discomfort is modeled through the disparity between the baseline and the optimal schedule. The mixed integer non-linear optimization model is built and solved with AIMMS software. Authors in [6] proposed a framework fo...

Optimal tuning of proportional integral controller for fixed-speed wind turbine using grey wolf optimizer

“…The chromosomes of constant lengths are generated as populations or the proposed candidate solutions to the PI optimal gains. Besides, the fitness of each chromosome is ranked based on the objective function [38] ITSE, before the application of operators. The operational steps of GA for finding the optimal gains of the PI controller in an optimization process are initialization, evaluation of the fitness of each chromosome, producing offspring using crossover and mutation [2].…”

Towards more accurate iris recognition system by using hybrid approach for feature extraction along with classifier

“…and a low-slung permit filter. From filter w outline four FIR filters of length 2N and of norm 1 equipped as unprotected in Figure 3 [25]- [27]. 𝑇 is the process of getting the coefficients as in ( 4) and…”

Applications of Nondominated Sorting Genetic Algorithm II Combined with WKNN Online Matching Algorithm in Building Indoor Optimization Design

“…The estimation technology accurately calculates the hourly building energy consumption required by the building's indoor environment by analyzing factors such as building indoor air conditions, indoor personnel activities, and outdoor weather data. Its core is the dynamic calculation process of energy consumption, making the simulation process of building energy consumption more accurate [ 32 ]. The dynamic energy consumption simulation process in the building's indoor environment includes the building energy consumption model, air conditioning system model, and equipment energy efficiency model.…”