Power system short term load forecasting based on Markov chain
Fan Yina · Journal of Qinghai University · 2012
Power system load forecasting is basic aspect in planning of city power grid;it is a prerequisite of ensuring reliable operation of power system,too.The key issue is to build proper mathematical models.A new method based on the combination of fuzzy clustering and Markov chain is presented.Status analysis of an object is carried out using the Markov chain,while fuzzy clustering is employed to the states of samples to suit the real case.According to state transfer,the load change is predicted.This algorithm is applied on power load forecasting in certain district of Qinghai province,and compared with real data.Simulation results show that the error can be limited to within 5%,which verify the high accuracy of application of Markov model to short-term load forecasting.