Research On Urban Electricity Load Forecasting And Medium And Low Voltage Distribution Network Planning Methods

Distribution network planning is one of the important works in the early stage of power system development,and it is of great significance to the regional economic and social development.As power demand increases,a proper and rational plan to transform the power distribution network can effectively balance power supply and demand,improve the reliability and security of power supply,and promote the development of the national economy.Shenyang City,located in the northeast of Liaoning province,is the provincial city of Liaoning province and the national industrial base.Therefore,rational planning and effective construction of the Shenyang distribution network have high economic and social benefits.This thesis studies the planning work of 2019-2024 of medium and low voltage distribution networks in Shenyang,including the analysis of the current status of the distribution network,power load prediction,planning scheme,and planning evaluation.Firstly,the present situation of the Shenyang distribution network is analyzed in detail to find out the main problems existing in the distribution network.Secondly,the thesis analyzes the Shenyang power load characteristic,studies the application of time series and BP neural network algorithm in the medium and long-term load forecasting,and aims to improve the existing deficiency of BP neural network algorithm.Using time-series method,the standard BP neural network algorithm,and the improved BP neural network algorithm to conduct load forecasting of Shenyang,this thesis finds that improved variable vector of BP neural network algorithm has higher accuracy and is more stable.Then,a comprehensive analysis of the distribution network planning goal and the technical guideline of Shenyang is performed based on Shenyang load forecasting results and main problems of the distribution network of 60 kV,10 kV,0.4 kV power distribution network planning.For 66 kV power distribution networks,substation planning based on minimum cost model is studied with network programming based on binary particle swarm optimization(PSO)algorithm,and the results meet the location and network programming "N-1" check and optimize Shenyang 66 kV power network structure.For 10 kV distribution network,the study,by combining load prediction results and load capacity ratio requirements,determines the load supply of 10 kV distribution network,obtains the new distribution transformer and line scale of each power supply area in the planned year,and gives the target network connection mode.For the 0.4 kV distribution network,considering the situation of new distribution transformers and the construction requirements of power lines,cable lines are primarily considered for low-voltage lines in Shenyang,and the number of new lines in the low-voltage distribution network should be given.Finally,the planning results are evaluated from the aspects of power supply reliability,line loss rate,and network frame target,etc.The evaluation results prove that the planning is rational and meets the demand of Shenyang electric power economic development.