Research On Medium And Long-term Power Load Forecasting And Distribution Network Planning In Tieli City Area

Power load forecasting is one of the important tasks of the power sector,which provides auxiliary functions for the formulation and implementation of national energy layout and economic development strategies.For power grid planning,especially medium and long-term power load prediction is the most important.At the present stage,there are problems such as difficult to guarantee model accuracy,slow speed of technical change,and lack of cutting-edge technology exploration.During the “13th Five-Year Plan period”,the economic development of Tieli city exceeded experts’ expectations,leading to the existing distribution network with prominent problems such as weak network structure,poor power quality and old power grid equipment,which cannot meet the growing demand for electricity.In view of the above problems in Tieli city,this paper selects the medium and long-term-load prediction algorithm based on neural network to make load prediction,and plans the local power grid through the predicted load data.The main work content of this paper is as follows: First,the medium and long-term load forecast of Tieli City.According to the current mainstream medium and long term load prediction method,BP neural network algorithm(back-propagation,BP)is selected through the algorithm characteristics,Matlab software and the current region,and the medium and long term load prediction scheme is combined with historical data.Then,the distribution network planning scheme that can meet the economic development of Tieli city was formulated.Through the analysis of the current situation of the local power grid,the deficiencies of the local power grid were found.According to the principle of power supply area division,the division of power supply area in Tieli City was determined and the key points of power grid planning were defined.Finally,the effect of the planned distribution network architecture is verified.When Simulink is selected to model and analyze the distribution network architecture before and after planning,we can know that the power factor of each node is improved and the purpose of planning is achieved.At the same time,the “N-1” pass rate of the planned 10 kV line and the maximum short-circuit current of the 10 kV bus are improved.In this paper,the medium-and long-term load forecasting and distribution network planning of Tieli City,combined with the target grid frame,divides Tieli City into C and D power supply areas,and the planning status year is 2021,the planning period is 2022～2030,and the planning level year is 2030.The BP neural network algorithm predicts that the maximum electricity load in Tieli City in 2030 will be 167.14 MW,and the total electricity consumption will be 590 million k W·h.According to the predicted results of the distribution network planning,the substation capacity ratio is between 1.8～2.0,the distribution is reasonable,the 10 kV trunk line “N-1” pass rate increased by 23.2%,through Simulink modeling simulation analysis of the distribution network in the area found that the power factor of each node before the planning is 0.8,which does not meet the power factor requirements of the power grid,and the power factor is increased to 0.95 after the planning,which meets the "Technical Guidelines for Distribution Network Planning and Design"(Q/GDW).1738-2020)requirements,improve the power quality of users in the region and improve the reliability of power supply.