A Swarm Intelligence Approach to the Power Dispatch Problem

Abstract

This paper examines how two techniques of the Particle Swarm Optimization method (PSO) can be used to solve the Economic Power Dispatch (EPD) problem. The mathematical model of the EPD is a nonlinear one, PSO algorithms being considered efficient in solving this kind of models. Also, PSO has been successfully applied in many complex optimization problems in power systems. The PSO techniques presented here are applied to three case studies, which analyze power systems having four, six, respectively twenty generating units.

A Modified Harmony Search Algorithm for the Economic Dispatch Problem

“…In order to verify if MHS algorithm works in similar conditions like any other method M, the following relation is used: For the test system 1, it is assumed that ε=10 -10 MW can be neglected, meaning that all methods are being applied in similar conditions with respect to satisfaction of equality constraint (8). Table 4 shows a comparison between the results of MHS algorithm and three other optimization methods used for solving the same problem: particle swarm optimization (PSO) [6], multiple tabu search algorithm (MTS) [15] and differential evolution (DE) [16].…”

“…To cover these drawbacks several artificial intelligence-based optimization techniques were applied. One of the most frequently used methods is based on the particle swarm optimization (PSO) applied in classical, enhanced or hybrid versions: PSO, PSO with time varying acceleration coefficients (PSO-TVAC) [6][7][8], new PSO (NPSO, NPSO-LSR) [9,10], improved PSO [11], distributed Sobol PSO with tabu search algorithm (DSPSO-TSA) [12]. Other methods used for solving ED problems are: evolutionary programming (EPs) [13], biogeography-based optimization (BBO) [14], tabu search and multiple tabu search (TS, MTS) [15], differential evolution (DE) [16,17], hybrid DE (DEPSO) [18], artificial bee colony algorithm (ABC) [19], incremental ABC with local search (IABC-LS) [20], harmony search (HS) [21], differential HS (DHS) [22].…”

Environment Friendly BB-BC Optimized Economic Dispatch with Real and Reactive Power Constraints

“…[10], [11]. Consider that the number of birds searching food in a field and the food is located only at one point in that field also all the birds are not aware of the location of food but they know the distance of food, so the best way for finding the food is to follow the bird, which is nearest to the food.…”

Improved ACO Algorithm with Pheromone Correction Strategy for the Traveling Salesman Problem

“…There are also a number of engineering design problems with mixed continuous and discrete variable and nonlinear objective function and nonlinear constraints that are used as benchmarks for optimization algorithms. For such intractable problems acceptable suboptimal solutions can usually be found by some metaheuristics, recently very successfully by nature inspired algorithms and as a subclass, swarm intelligence algorithms which include artificial bee colony [1], [2], particle swarm optimization [3], [4], cuckoo search algorithm [5], [6], seeker optimization algorithm [7], [8] etc.…”