Multi-power Optimal Scheduling Based On Improved Fruit Fly Optimization Algorithm

With the rapid development of economy and the depletion of conventional energy,how to effectively utilize renewable energy such as wind energy,solar energy and water energy has been paid more and more attention.However,the output of wind power and photovoltaic power is random and unregulable,which will increase the uncertainties of the system and affect the stable operation of the system.So,it is necessary to adjust the traditional dispatching mode to meet the operation requirements of power systems with multiple power sources.In this paper,multi-power optimal scheduling problem is studied..Firstly,the indirect method is used to predict the power of wind farm.The prediction tool is Least Squares Support Vector Machine(LSSVM).The results of relative error,average absolute percentage error and root mean square error prove the rationality of the selected embedding dimension and the feasibility and practicability of LSSVM in the field of wind power prediction.Secondly,an improved Fruit Fly Optimization Algorithms(FOA)is proposed,which can be better applied to solve complex economic Dispatch(ED)problems.The mathematical model of traditional economic dispatch is established and a heuristic strategy is designed to deal with constraints.By solving the test system with different characteristics and comparing with the optimization results provided by other literatures,it is shown that the improved FOA has strong optimization ability when dealing with the test system with different characteristics.It is proved that this algorithm has stronger optimization ability than other algorithms and can solve more complex ED problems more effectively.Finally,this paper establishes an optimal dispatching model of wind,solar,hydrothermal and thermal storage multi-power sources with minimum operating cost and thermal power output fluctuation as the objective function.In order to reduce the difficulty of solving the model,encourage clean energy to go online first and ensure the operation efficiency of thermal power units,a method for determining the number of dispatching units of thermal power units is designed.Then the improved FOA is used to optimize the dispatch of four multi-power system models with different power types,and the dispatch results are compared and analyzed economically and output fluctuation.which is helpful to formulate a more comprehensive and effective dispatch plan.