To protect power lines, distance relays are used which can rely on a modified distance resistance. But usually the operating range of these relays changes as the network conditions change (network topology, load value, output value, etc.) and leads to false trips, by using methods that can process information and recognize patterns. For example, the use of micro and intelligent processor algorithms can use the new relays with high precision and thus provide adequate protection. In this study, a distance relay was modeled using a neural network, and it was observed that the neural relay had higher accuracy than the conventional relay. In addition to detecting the fault and its location, type and phase of the fault, three-stage simultaneous protection can be performed. As a result, the number of linear relays can be reduced by using relays based on neural technologies. An MLP (multilayer perceptron) neural network is used to model a sequence of distances.

In recent decades, in the process of restructuring energy systems, centralized energy sources are being replaced by decentralized ones. This led to the emergence of a new concept (power generation) in power supply systems, especially in distribution systems, known as «distributed generation». Distributed generation was introduced into the power systems, especially at the low voltage level, to make them more reliable, safer and efficient. At the same time, various problems appeared in the power supply systems that require solving issues of ensuring the selectivity and sensitivity of the protection action, maintaining the required voltage level. Since the current and future trends in the development of electric power systems are aimed at increasing the integration of distributed generation, especially through installations, made based on renewable energy sources, it is required to conduct studies on the impact of these generation technologies on the distribution networks. When using distributed generation, setting up the protection system is associated with the problems associated with changes in the magnitude and direction of emergency currents. Distributed generation installations affect the fault current in a certain way, while influencing the overcurrent protection systems in terms of their coordination. In this regard, the alternative protection systems and algorithms can be used, such as directional overcurrent relays. In addition, highly penetrating distributed generation devices such as photovoltaic installations can cause overvoltage in the distribution systems, which must be effectively prevented. Thus, the paper considers the problems caused by the distributed generation and related to protection systems and voltage regulation in the distribution networks. Solutions for mitigating the negative impact of distributed generation on the power supply systems are proposed and considered in detail.

Current trends in the development of power supply systems for industrial facilities when applying the principles of distributed generation consist in the implementation of power supply from several power sources of different types and characteristics (photovoltaic cells, wind power plants, microturbine plants, diesel power plants), the maximum approximation of power sources to electrical loads, the use of electricity storage. The availability of such installations near consumers reduces the quantitative energy consumption by reducing the technical losses of the ge¬nerated energy and reducing dependence on fossil fuels. However, with these advantages, distri¬buted generation has created technical problems, one of which is the complication of relay protection systems due to the possibility of powering the damage point from different sides. This circumstance requires the development of new algorithms and protection schemes to ensure selectivity and to increase the sensitivity of relay protection. The purpose of the study is to analyze the algorithms of remote protection in distributed generation systems. The methods used comprise an integrated approach, including scientific analysis, processing and analysis of the results of theoretical and experimental studies in the field of relay protection of electrical complexes in networks with distributed generation. The results obtained present the analysis of various algorithms for the implementation of protection, which were implemented as proposals for distribution networks. The system of remote protection in networks containing distributed generation systems is presented, and the algorithms of operation are compared to increase the sensitivity of remote protection devices to the occurrence of various emergency modes: single-phase and three-phase short circuits. Several algorithms for increasing the sensitivity of remote protection for distribution networks in the presence of several power sources are considered. The comparison of these algorithms according to the criteria of the implementation cost, the accuracy of implementation, the number of necessary input data is also carried out. Practical significance of the research the research results can be used to take into account the effect of changes in the parameters of protected connections under conditions of electrical complexes operation in a network with distributed ge¬neration on the effectiveness of remote protection. They make it possible to increase the sensitivity and selectivity of the remote protection operation in case of emergency situations.

The increasing expansion of the use of renewable distributed generation (RDG) technologies in electrical networks such as solar plants or wind farms and others has changed the nature of the distributed system and transformed it from the traditional system into an efficient system. This system has led to various technical effects in the host networks, with regard to voltage, electrical energy losses, fault levels, stability and electrical energy quality. These effects are not generic to any network; It can be positive, negative or neutral depending on the structure of the studied network, its operational condition and the various technology of the distributed generators. This research aims to quantitatively correct the effects of (RDG) in terms of voltage and electrical energy losses in the host networks. , since efficient distribution systems contain generators of a special nature and often contain bidirectional flux energy, it was necessary to construct a mathematical model of the distribution system hosting RDG units, which is fundamentally different from the traditional model of defining the reference electrical distribution bus bar. In order to achieve the systematic analysis, evaluation criteria and indicators were determined and mathematical formulas for them were completed. Based on the accomplished mathematical basis, an algorithm designed in such a way that it can be applied to any multi-voltage distribution system and to different distributed regenerative generation techniques is proposed. To demonstrate the algorithm's capabilities, it was tested on typical distribution networks using Factory Power DigSilent software, which is somewhat similar to MATLAB but more suitable for large capacity systems.

To protect power lines, distance relays are used which can rely on a modified distance resistance. But usually the operating range of these relays changes as the network conditions change (network topology, load value, output value, etc.) and leads to false trips, By using methods that can process information and recognize patterns, for example, the use of micro and intelligent processor algorithms can use the new relays with high precision and thus provide adequate protection. In this study, a distance relay was modeled using a neural network, and it was observed that the neural relay had higher accuracy than the conventional relay. In addition to detecting the fault and its location, type and phase of the fault, three-stage simultaneous protection can be performed. As a result, the number of linear relays can be reduced by using relays based on neural technologies. An MLP (multilayer perceptron) neural network is used to model a sequence of distances.