CONTROL OF THE CAPACITY OF THE POWER GRID IN THE TASKS OF FORECASTING THE ELECTRICAL LOAD

Abstract

The paper considers the software-modeling complex of the power grid management system and
its elements. The relevance of the work is due to the requirements of the current legislation for forecasting
electricity consumption to solve the problem of maintaining a balance of capacity between
the generating side and electricity consumption. The developed algorithms and control methods are
used as part of a software-modeling complex for managing the power grid and power equipment, the
most relevant is the use of autonomous consumers and micro-grids in local power systems. For the
effective conduct of experimental research, an experimental methodology was developed, including
the stage of development of the experimental plan-program; the choice of means of conducting the
experiment; conducting the experiment; processing and analysis of experimental data. It is shown
that it is possible to use the technical and information basis of a hierarchical automated information
measuring system for monitoring and accounting of electricity to build a technological management
system of a regional grid company. It is shown that the smart meters of the intelligent electricity metering
system (ISU) are in continuous communication with the producer and consumer of energy, that
is, monitoring takes place in real time. The developed neural network model (NS) model reduces the
task of short-term forecasting of power consumption to the search for a matrix of free coefficients by
training on available statistical data (active and reactive power, ambient temperature, date and index
of the day, predictive estimates of power consumption of the forecasting model, some connections, the
power system of the magnitude of the consumed active and reactive power has an acceptable level of
prediction error. A neural network has been developed to estimate the capacity, calculate and predict
the temperature of the cores of a power cable line in real time based on data from the temperature
monitoring system, and taking into account changes in the current load of the line. The analysis of
the obtained characteristics showed that the maximum deviation of the data received from the neural
network 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 of
the chosen network model and its applicability in practice for the reliable operation of the cable system
of power supply to consumers. The analysis of the results showed that the more the insulation
material of the power cable line is aged, the greater the temperature difference between the original
and the aged sample.