Power Load Forecast Model of Genetic Neural Network Based on Tabu Search

The neural network has been applied to the area of power load forecast successfully, but it has such disadvantages of local optimization and slow convergence speed. A new kind of genetic neural network forecast model based on tabu search was proposed for overcoming those disadvantages. Utilizing the global optimizing ability of genetic algorithm and the memory function and ability of mountain climbing of tabu search, it defined a tabu aberrance operator and constructed a mixed genetic tabu algorithm, which can solve the above disadvantages of neural network and the premature problems of genetic algorithm, to train the weights and thresholds of neural network. Comparing with normal genetic algorithms, this genetic neural network based on tabu search achieved better forecast result.