The paper examines a possibility to optimize complex technological processes of energy resources transfer and consumption. Notes the importance of unidentified and weakly formalized factors consideration, which influence quality of the described object classes functioning. Suggests use of fuzzy neural networks and controllers on their basis for implementation of technological processes optimization of energy resources transfer and consumption at the expense of its dynamic accuracy forecast improvement. Presents algorithmic realization, that later on configured in the MATLAB simulated environment. Quantitative and qualitative parameters, which characterize fuzzy neural controller’s usage quality, were received. Later, software environment elements are being described, which constructed on the basis of the suggested adaptive approach for complex technological processes optimization. Points out a possibility to conduct comparative study, and also simulation modeling implementation by way of presented solutions.

The implementation of 'Smart Objects' is an important part of the development of adaptive Smart Grid structures. For this class of objects, poorly for malizable factors, such as microclimate parameters, environmental indicators, and consumer load, acquire a significant influence. To solve this, PID controllers are usually used in Smart Objects; however, their accuracy is limited. Fuzzy neural controllers are an alternative solution for the integrated optimization of Smart Objects. This article proposes a scalable model of Smart Object equilibrium by the example of basic utility systems (heating, air conditioning/ventilation and illumination). It was found that the use of fuzzy neural controllers in such systems makes it possible to improve their efficiency by increasing the accuracy of energy consumption forecasts. Control systems based on PID controllers and fuzzy neural controllers in Smart Object were comparted only to find that the latter have a higher accuracy.

The article addresses optimization of power supply systems by using fuzzy neural networks to increase the accuracy of operational forecasts and implement active control systems in the power supply grids. As a practical example, the article considers the optimization of parameters of the 220 kV Yuzhnaya Substation operated by the Regional Dispatching Office of the Voronezh Region Electric Power System (Voronezh, Russia). The obtained results indicate an increase in the energy efficiency of the studied equipment by 4.38% (in terms of real power loss),as compared to the existing control mode, through the use of fuzzy neural controllers that improve the accuracy of forecasts of the relevant technological parameters. The developed solutions can be used in electrical power systems and load nodes as a part of control modules. The economic effect is achieved by taking into account the poorly for malizable factors and compensating for their impact on real power loss in the transformer equipment.

This article discusses the possibilities of optimizing the fuel and energy complex by improving the accuracy of the forecast of the state in both the operational and medium-term periods: from an hour to several years. The model used to implement the mentioned energy efficiency improvement is based on the use of fuzzy neural networks together with the function of minimizing power losses in the elements of electric power systems. The Mamdani modification is used, which takes into account the database of previous periods of the system state, represented as static load characteristics. The organization of this approach allows you to take into account weakly formalized factors, thereby improving the quality of forecasting and dispatching management. At the same time, it is possible to use models for a wide class of objects, which is achieved due to its scalability. The estimation of forecasting accuracy of the proposed approach exceeds similar indicators of currently used statistical methods and regression implementations. These factors are direct economic drivers of reducing production costs.

No abstract