Solving Multiobjective Optimization Problems Using an Artificial Immune System
Genetic Programming and Evolvable Machines
Multi-objective genetic algorithms: Problem difficulties and construction of test problems
Evolutionary Computation
Hi-index | 0.00 |
Power network planning is a discrete, nonlinear and multi-object mixed integer program problem, and is quite difficult to solve. In this paper, a Multi-objective Problem Evolutionary Algorithm, MOPEA, for solving power network planning is presented according to the principle of particle trajectories, minimum energy principle and the law of entropy increasing in phase space of particles based on transportation theory and this algorithm can solve complex optimization problems to obtain the global optimal solution. By means of a DC load flow model, the network takes into account of construction cost, operation cost and cost of losses. After running a simulation computation of Garver-6 node system, the results are: Compared with the results of single objective genetic algorithm and NSGA-II algorithm, MOPEA obtains the lowest costs of total planning scheme, and the planning schemes can highly improve the economic efficiency of power transmission network planning.