УПРАВЛЕНИЕ ПРОПУСКНОЙ СПОСОБНОСТЬЮ ЭНЕРГОСЕТИ В ЗАДАЧАХ ПРОГНОЗИРОВАНИЯ ЭЛЕКТРИЧЕСКОЙ НАГРУЗКИ

Abstract

The paper considers the software-modeling complex of the power grid management system andits elements. The relevance of the work is due to the requirements of the current legislation for forecastingelectricity consumption to solve the problem of maintaining a balance of capacity betweenthe generating side and electricity consumption. The developed algorithms and control methods areused as part of a software-modeling complex for managing the power grid and power equipment, themost relevant is the use of autonomous consumers and micro-grids in local power systems. For theeffective conduct of experimental research, an experimental methodology was developed, includingthe stage of development of the experimental plan-program; the choice of means of conducting theexperiment; conducting the experiment; processing and analysis of experimental data. It is shownthat it is possible to use the technical and information basis of a hierarchical automated informationmeasuring system for monitoring and accounting of electricity to build a technological managementsystem of a regional grid company. It is shown that the smart meters of the intelligent electricity meteringsystem (ISU) are in continuous communication with the producer and consumer of energy, thatis, monitoring takes place in real time. The developed neural network model (NS) model reduces thetask of short-term forecasting of power consumption to the search for a matrix of free coefficients bytraining on available statistical data (active and reactive power, ambient temperature, date and indexof the day, predictive estimates of power consumption of the forecasting model, some connections, thepower system of the magnitude of the consumed active and reactive power has an acceptable level ofprediction error. A neural network has been developed to estimate the capacity, calculate and predictthe temperature of the cores of a power cable line in real time based on data from the temperaturemonitoring system, and taking into account changes in the current load of the line. The analysis ofthe obtained characteristics showed that the maximum deviation of the data received from the neuralnetwork from the data of the training sample was less than 3%, which is quite an acceptable result.The comparison of the forecast values with the actual ones allows us to speak about the adequacy ofthe chosen network model and its applicability in practice for the reliable operation of the cable systemof power supply to consumers. The analysis of the results showed that the more the insulationmaterial of the power cable line is aged, the greater the temperature difference between the originaland the aged sample.