Artificial intelligence application to security control in power systems
thesis
posted on 2023-05-27, 20:55authored byLe, TL
In power system operation, steady state security control is employed to provide continuous supply to customers and avoid damage to power system plant. The steady state security control includes detection and alleviation of transmission equipment overloads and bus voltage violations. The three main functions of the security control, ie. security monitoring, contingency analysis and control action analysis, can be performed by an experienced system operator with the use of conventional optimisation methods. However, such methods require large computation time and rely on mathematical models and sophisticated programming techniques. They can only cover the analytical part of solutions, leaving the burdensome task of making numerous judgements to the system operator. These methods may not be used for real-time control of large power systems; in particular, under emergency and abnormal operating conditions when significant human expertise is required but due to emotional stress is not readily available. Thus, there is a need for new methods and tools such as decision-support systems, to improve the computational speed and assist operators in making prompt and correct decisions on control actions under emergency and abnormal conditions. During the last decade the computational approach to artificial intelligence (AI) has undergone a significant evolution. Results obtained from the international surveys on AI applications in power systems show that an interest in applications of Al to power system problems is growing strongly. Al is a promising technology that will be able to fill the gap between human capabilities and difficulties involved in the daily operation and planning of modern power systems. The work presented in this thesis addresses the aspects of Al applications to steady state security control in power systems. This research focuses on two major issues. Firstly, analysis of the methods employed in steady state security control and identification of potential Al applications where the existing methods are deficient. The second task is the development of decision-support systems to incorporate operator knowledge, provide an interactive-mode interface to users, and improve the computational speed. Three decision-support systems have been developed: ‚Äö an intelligent system for determination of short-time thermal ratings and permissible overload duration of transmission lines using the rule-based expert system and artificial neural network. ‚Äö a prototype expert system for transmission line overload alleviation using database, rule-based, and sensitivity tree approaches. ‚Äö a prototype expert system for voltage control and reactive power compensation using rule-based and sensitivity tree approaches. The following methods have been proposed and implemented in the development of the above decision-support systems: ‚Äö Determination of permissible overload duration of transmission lines based on the short-time thermal rating. ‚Äö Estimation of instantaneous solar radiation employed in the determination of thermal rating of transmission lines using artificial neural network and regression techniques. ‚Äö Estimation of the distance to a voltage collapse using the stability margin analysis. ‚Äö Automatic allocation of static and dynamic reactive power compensation to improve solution of voltage security and stability control. ‚Äö Reduction of the computation time for voltage and reactive power control using the \three-tier\" network equivalencing technique. The decision-support systems have been successfully tested on several power systems such as the IEEE 30-bus AEP 57-bus and real 293-bus power system of the Hydro-Electric Commission of Tasmania. Results obtained show that the decision-support systems provide fast and correct solutions with advice on control actions expressed in the natural language form. Therefore the intelligent systems developed can be effectively applied to assist operators in the detection and alleviation of line overload and bus voltage violation problems in power systems. Nineteen refereed technical papers have been published including three in international scientific journals. The research results have been applied to current practice in the Hydro-Electric Commission of Tasmania for planning and operation studies."
Copyright 1996 the Author - The University is continuing to endeavour to trace the copyright owner(s) and in the meantime this item has been reproduced here in good faith. We would be pleased to hear from the copyright owner(s). Addresses the aspects of artificial intelligence applications to steady state security control in power systems. It focuses on two major issues. First, analysis of the methods employed in steady state security control and identification of potential AI applications where the existing methods are deficient. Secondly, development of decision-support systems to incorporate operator knowledge, provide an interactive-mode interface to users, and inprove the computational speed. Thesis (Ph.D.)--University of Tasmania, 1996. Includes bibliographical references. Addresses the aspects of artificial intelligence applications to steady state security control in power systems. It focuses on two major issues. First, analysis of the methods employed in steady state security control and identification of potential AI applications where the existing methods are deficient. Secondly, development of decision-support systems to incorporate operator knowledge, provide an interactive-mode interface to users, and inprove the computational speed