Research On Short-term Load Forecasting And Operation Optimization In Low-voltage Substation Area

In order to reduce energy waste,improve energy utilization efficiency and ensure power supply security,short-term power load forecasting and system optimal operation are essential.Efficient and accurate short-term power load forecasting can improve the stability and reliability of power system operation,and it is also one of the methods to deal with the imbalance between supply and demand of power resources and improve operation efficiency.It can be used in power system dispatching,real-time control,making operation and development plans and other aspects.The optimization of system operation is an effective method to ensure the safe and stable operation of the system and realize the economic operation of the system.Aiming at the low accuracy of short-term load forecasting in low-voltage substation area,a time convolution network short-term load forecasting model based on variational mode decomposition is proposed.Through the variational mode decomposition of the original load sequence after processing,a better regularity subsequence is obtained to reduce its impact on the overall short-term power load forecasting.Then,the maximum information coefficient is used to determine the maximum temperature,average temperature,minimum temperature and relative humidity as the main influencing factors of the load,and the processed historical load data and the decomposed sub series are used as the input of the prediction model.The average absolute percentage error and root mean square error are used to evaluate the prediction results.At the same time,whether the load data is subject to variational mode decomposition under the condition that other input data are unchanged is guaranteed to form two kinds of input load data sets.Combined with the actual example data,the short-term load forecasting experiments of time convolution network,short-term memory network and gated cycle unit are conducted respectively,the experimental results prove the superiority of the prediction model proposed in this paper and the effectiveness of the variational modal decomposition.Aiming at the problem of high operation cost of low-voltage substation area system,through the mathematical modeling of wind turbine,photovoltaic array,micro gas turbine and energy storage device in the substation area,and combining with various constraints,a daily economic optimal dispatching model of low-voltage substation area system with the goal of economy is constructed.Then,according to the characteristics of the model,the linear programming software CPLEX is used to solve it.Different scheduling schemes are designed,and the punishment of abandoning wind and light as well as carbon transaction cost are considered in the operation cost,which is brought in and solved through actual data.The final optimization results show that the operation cost of the low-voltage substation area is the lowest under the condition of coordinated operation of wind,solar and gas reservoirs,which can provide a theoretical reference for the economic operation of the low-voltage substation area system.