Cloud Theory Based Load Frequency Control In Interconnected Power System With Renewable Energy

Nowadays,the output of renewable energy is highly uncertain and difficult to predict.When large-scale renewable energy sources with strong uncertainties are involved,the control quality of traditional LFC controllers declines and the operational requirements cannot be met.This paper focuses on the research of load frequency control after the injection of high ratio renewable energy sources into the grid.Therefore,based on the theory of artificial intelligence with uncertainty,the cloud model algorithm proposed in this paper is aimed at solving the problem of LFC controller quality degradation caused by uncertainties in the actual power system operation,so as to meet the ever-increasing scale of renewable power integration and increase the penetration of renewable energy.Firstly,this paper introduces the cloud model theory and its application,and uses the cloud model algorithm as the main technical method to deal with the uncertainty of power system operation.Cloud theory solves uncertain problems by skillfully combining probability statistics with fuzzy theory.Instead of using accurate membership degree,cloud model transforms the qualitative concept into quantitative data and takes a random number within a small range close to a specific value.Therefore,cloud model theory including both fuzziness and randomness,can compensate the insufficiency in solving uncertainty problems.Secondly,this paper proposes a PI control method by using planar clouds and presents an intelligent adjusting strategy for an interconnected power system which includes renewable energy generations.In this method,the deviation and its rate of change are taken as the front part of cloud generator while the consequent part is composed of the variation of PI parameters.And then,the clouds reasoning rules are made based on the artificial engineering experience and contribute to the design of the cloud controller.On the Matlab platform,the proposed PI controller is compared with the traditional PI controller under different load disturbances.As a result,it can meet the performance requirements of the LFC in the interconnected power systems better.Finally,in order to effectively improve the penetration of renewable energy resources,this paper proposes a Cloud-Neural Network PI control method for interconnected power system with renewable energy.The proposed cloud neural network algorithm based on cloud theory to solve the adverse effects of uncertainties.In addition,the proposed cloud neural network algorithm can learn cloud control rules by itself,improved previous planar clouds PI controller.Compared with planar clouds algorithm,this new algorithm retains self-learning function of the neural network and does not depend on artificial experience.On the Matlab platform,comparison of Cloud-Neural Network PI controller,Planar cloud PI controller and traditional PI controller is made in complex nonlinear power system,and simulation results show that proposed Cloud-Neural Network PI controller has strong adaptive and self-learning capabilities,presenting better robust performance and dynamic-static characteristic.