Electric energy supplied by energy-supplying organizations to consumers under contracts acts as a special kind of product, characterized by a coincidence combination of timely production, transportation and consumption, as well as -ability to store and return it. Accordingly, as the product of any kind, the concept of “quality” applies to electricity. The deviation of power quality from established standards worsens the operating conditions of electrical installations of both the network and consumers. One of the main and most important regime parameters determining the quality of electricity are asymmetry and non-sinusoidal pressures in triple phase networks. These pressures lead to additional voltage deviations at the terminals of consumers, increased losses in network elements and electric receivers, and deterioration of the operating conditions of electrical equipment. In this regard, we are presented with the problem of assessing the damage from low-quality electricity, which is expressed in additional losses of electrical energy and in reducing the service life of equipment. Therefore, to solve this problem, it is necessary to measure the quality of electrical energy at the substation, and to estimate how much distribution network losses will increase in comparison with the network operation mode, where the quality indices of electric power quality do not exceed permissible limits, and how this may shorten the equipment’s service life. For this purpose, we use a mathematical apparatus (device/equipment?) based on neural networks. A neural network was constructed to predict the economic indicators of the electric network and the compatibility of consumers with it. A method has been developed that can evaluate and predict the signs of the main and additional indicators of the quality of electrical energy, and the network can provide a reduction in costs in the prevention of emergencies. The results of these studies can be used in various areas for forecasting the parameters of technical systems and aggregates, and used to prevent emergencies. A neural network has been constructed that allows the use of information about the 0.38 / 0.22 kV network mode in real time. And if necessary, it can also be used to control the network mode, in order to reduce the imbalance of currents and to reduce additional losses of electric energy.
Key words: neural network, forecasting, quality of electrical energy.