An improved load forecasting method of warship based on GA-SVR

摘要

An improved forecasting method base on genetic algorithm and support vector machine for warship short-term load forecasting was presented and tested. The new influencing factors of warship power load were used in modeling which is different with the land grid and civilian vessels grid. Theory of genetic algorithm and Support vector machine was disscused first, and the method of genetic algorithm was improved to have the ability of adaptive parameter optimization. and the method of support vector machine was improved by the adaptive GA optimizational method. then a new adaptive short-term load forecasting model was established by the adaptive GA-SVM method. finally Through simulation results show that the adaptive GA-SVM method is highly feasible to predict with high accuracy and high generalization capability.