Demand Side Management Using Bacterial Foraging and Crow Search Algorithm Optimization Techniques

Enhanced Bacterial Foraging Optimization Based on Progressive Exploitation Toward Local Optimum and Adaptive Raid

“…x current = new_location, and fitness current = new_fitness,if new_fitness is better than fitness current step_size = step_size/mul_1, and n = n + 1, if new_fitness is not better than fitness current break out of the loop, if n > mul_2 new_location = x current + step_size * Direction, and continue the loop, if n <= mul_2 (11) where, Loop means the start of a loop; fitness current is the fitness of current bacterium; mul_1 is a preset parameter to reduce the step-size during the period of swimming(in this paper, it is set at 10); n is a parameter that controls the number of the step-size to be reduced, and its starting value is set to 1. mul_2 is a preset parameter, which means the allowed maximum number of reducing the step-size. By comparing Fig.…”

“…And the loop about swimming will be continued until the controlling parameter n is bigger than mul_2 according to Eq. (11).…”

“…In paper [10], authors propose a solution to the menu planning problem adapting the bacterial foragingbased optimization algorithm and the results obtained were satisfactory from an expert's point of view. In paper [11], BFO was adopted to handle with the problem about high consumption of energy and energy crisis by shifting the load from on peak hours to off peak hours in demand side management, then the electric cost can be reduced and electric load can be better dispatched and managed, accordingly simulation results show that BFO is perform better than Crow Search Algorithm in reducing the total cost and peak average ratio and archived the objectives. In paper [12], a chaotic bacterial foraging optimization was integrated with Gauss mutation approach termed CBFO-FKNN, which efficiently resolved the parameter tuning issues of the FKNN(fuzzy k-nearest neighbor) and the simulation results indicated the proposed approach outperformed the other five FKNN models based on BFO, PSO(Particle Swarm Optimization), GA (Genetic Algorithm), fruit fly optimization and firefly algorithm, and will bring great convenience to the clinicians to make a better decision in the clinical diagnosis.…”