Neural Network Model for Evaluating Thermofluctuation Processes in Cable Systems Using a Multi-stage Forecasting Method

The chapter is a continuation of the consideration of the practical application of the elements of digital energy. The main focus of the work is on cyber-physical systems. A neural network (NN) was developed to assess the throughput, calculate and forecast the core temperature of a power cable line (PCL) in real-time based on data from a temperature monitoring system, and taking into account changes in the current load of the line. An analysis of 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 an acceptable result. A comparison of forecasted values with actual ones allows us to talk about the adequacy of the selected network model and its applicability in practice for reliable operation of the cable power supply system of consumers. An analysis of the results showed that the more aged PCL insulating material (IM) is the greater the temperature difference between the initial and aged sample.