Daniil Panasetsky

A random forest-based approach for voltage security monitoring in a power system

Voltage collapse is a critical problem that impacts power system operational security. Timely and accurate assessment of voltage security is necessary to detect alarm states in order to prevent a large-scale blackout. This paper presents an on-line voltage security assessment scheme using periodically updated random forest-based decision trees. We demonstrated the proposed method on the modified 53-bus IEEE power system. Results are presented and discussed.

A hybrid artificial neural network for voltage security evaluation in a power system

A majority of recent large-scale blackouts have been the consequence of instabilities characterized by sudden voltage collapse phenomena. This paper presents a method for voltage instability monitoring in a power system with a hybrid artificial neural network which consist of a multilayer perceptron and the Kohonen neural network. The proposed method has a couple of the following functions: the Kohonen network is used to classify the system operating state; the Kohonen output patterns are used as inputs to train of a multilayer perceptron for identification of alarm states that are dangerous for the system security. The approach is targeting a blackout prevention scheme; given that the blackout signal is captured before it can collapse the power system. The proposed method is realized in R and demonstrated the modified IEEE One Area RTS-96 power system.

Preventive and emergency control of intelligent power systems

The adaptive emergency control concept is based on realization of a tradeoff between preventive and emergency control by combining preventive and emergency actions. The paper proposes to complement the existing control strategies by predictive control strategy - adaptive emergency control, which implies identification of the emergency, until the emergency has occurred. In this paper presented the smart predictive voltage stability assessment (VSA) for the adaptive emergency control techniques on the basis of the artificial neural network methodology. The main idea of the smart predictive VSA here is a creation of a neural network model, based on a self-organized Kohonen map SOM that will be able to perform monitoring and prediction of emergency condition. Simulation results are obtained by the proposed scheme for different power system networks to assess the security level of the network.

Smart Technologies in Emergency Control of Russia's Unified Energy System

The objective trends in electric power systems (EPSs) call for prompter and more adequate response of control systems. New smart measurement, communication and control tools, information and computer technologies can be used to improve EPS controllability. The distinctive features of the Unified Energy System (UES) of Russia are discussed and the current emergency control system is presented in the paper. A modern approach to monitoring, forecasting and control is suggested. Some artificial intelligence applications for development of emergency control in the UES of Russia are presented.

A Multi-Agent Approach to Electric Power Systems

Electric power systems are rather complicated objects for modeling, investigation and control because of many elements and complex structure. Comprehensive multi-functional software is necessary to study multi-dimensional systems of the kind. The problems of current state estimation should be solved for monitoring of electric power system operation conditions. Emergency control actions are required to improve stability of electric power systems. A multi-agent approach can be used to solve such complex problems of electric power systems. The chapter deals with the following important areas of modeling, investigation and control of large electric power systems: • Effective construction of comprehensive software by using the multi-agent approach; • Decomposition of state estimation problem for large electric power system by using phasor measurement units and the multi-agent approach; • Multi-agent approach to coordination of emergency control devices against voltage collapse. The effectiveness of multi-agent approach for solving the above problems is illustrated by test examples.

Development of software for modelling decentralized intelligent systems for security monitoring and control in power systems

With rapidly increasing complexity of power grids in Europe, North America and Asia, liberalization of electricity markets and increasing penetration of renewable energy, the risk of large-scale emergencies and blackouts increases. This paper proposes a novel approach for development of software for modelling of decentralized intelligent systems for security monitoring and control in power systems. The innovation here is to joint use the modern computing environments - MATLAB, R and Java Agent Development Framework platform. The proposed intelligent system was tested on the modified 53-bus IEEE power system.

Short-term wind power forecasting based on T-S fuzzy model

Due to the impacts of wind speed, wind direction, temperature and pressure, it is uncertain and nonlinear for the wind power forecasting. To address these problems, this paper proposes a wind power short-time forecasting method based on the T-S fuzzy model, which does not rely on a large amount of historical data and can linearize the complex nonlinear process to obtain accurate results. In this method, the main affecting factors are selected by means of the correlation analysis for wind power prediction. Then, the antecedent and the consequent parameters of the forecasting model are identified by the fuzzy c-means (FCM) clustering algorithm and the recursive least squares method (RLS). Finally, the T-S fuzzy model for wind power short-term forecasting is obtained. The stationary wind periods are considered as the cases to validate the proposed forecasting method. The forecasting results are compared with the (support vector machine) SVM and the (empirical mode decomposition) EMD-SVM methods. The results show that the proposed T-S fuzzy model can effectively improve the precision of the short-term wind power forecasting.

On the problem of shunt reactor tripping during single- and three-phase auto-reclosing

The application of shunt reactors (both controlled and uncontrolled) on HVAC overhead transmission lines improves operational characteristics, but at the same time it brings the line closer to the resonance. Operation of the shunt reactor-compensated transmission line that is close to the resonance, causes a large number of problems which in particular can be solved by temporary tripping of the reactor(s). The article focuses on some aspects of the SF6 shunt reactor circuit breaker operations during one-phase and three-phase auto-reclosing. In particular, the problem of accident-free shunt reactor tripping, as well as possible ways to solve it are discussed.

Preventing large-scale blackouts in power systems under uncertainty

In modern electricity grids uncertainties only multiply. The ongoing deregulation and the expansion of renewable energy in power system worldwide require more complex control and decision making. As a result, large-scale blackouts still continue to happen. The authors deal with a topical issue: how to take the effective preventive actions given randomly changing circumstances in order to avoid power system cascading emergencies. In this paper, an intelligent viable approach is proposed to minimize the threat of large-scale blackouts under uncertainty. The proposed system can both serve the profit motive and prevent large-scale emergencies that arise from voltage instability. The developed system was tested on the modified IEEE One Area RTS-96 power system.

A new intelligent algorithm for load shedding against overload in active distribution networks

To improve power system reliability, it is important to reduce the amount of load shedding when a contingency occurs. Along with a comparison of the conventional load shedding methods, this paper presents an intelligent approach based on a centralized coordinated algorithm using a set of influence coefficients. The proposed method divides power system into a set of subsystems with the minimal mutual influence to minimize the amount of considered disturbances. A 28-bus test system is used to study the applicability of the proposed approach. A case study shows that the proposed algorithm can reduce the complexity and provide a high level of fault tolerance while keeping the required accuracy.