The authors [PS107 present an ANN method for the optimal reactive power control. The method is based on the Hopfield model which is used to solve the optimal reactive power compensation in this paper. It has been tested on IEEE-6 and IEEE-30 node systems and achieved a satisfactory result.
In the paper [PS108, in order to solve the voltage control problem, the authors propose an improved Hopfield model which has an individual input-output function for an individual neuron in order to achieve a drastic improvement in the calculation time.
The authors [PS109] introduce an ANN approach to voltage security monitoring and control. The ANN uses its association mechanism to approximate the complicated mathematical formulation of the voltage collapse phenomenon. The inherent parallel information processing nature of the ANN, which provides the capability of fast computation, enables the ANN approach to meet the rigorous demands of real-time monitoring and control. The IEEE 57 busbar system is used to demonstrate the applicability of the ANN approach to the problem of voltage security monitoring and control in power systems.
The authors [PS110] propose a new algorithm for VQ control using recurrent ANNs which has the ability to treat system dynamics. They propose the learning algorithm for inverse dynamics of a controlled target using recurrent ANNs. Secondly, they apply this algorithm to VQ control. They call this controller "neuroVQC". Finally, the usefulness of neuroVQC is shown in comparison with conventional VQ controllers.
In the paper [PS111
] an adaptive voltage regulator for power systems is proposed. The design of this regulator is based on variable structure control theory. To make the regulator adaptive to the power system operating conditions, an ANN is used. The effect of the proposed regulator has been compared to that of the realistic regulator system proposed by the IEEE Excitation Committee. The results are discussed and the opertaining recommendations are given.This paper presents an AI approach to the optimal VQ control. The method incorporates the reactive load uncertainty in optimizing the ovarall system performance. The ANN enhanced by fuzzy sets is used to determine the memberships of control variables corresponding to the given load values. A power flow solution will determine the corresponding state of the system. Since the resulting system state may not be feasible in real-time, a heuristic method based on the application of sensitivities in expert system is employed to refine the solution with minimum adjustments of control variables. Test cases and numerical results demonstrate the applicability of the proposed approach. Simplicity, processing speed and ability to model load uncertainties make this approach a viable option for on-line VQ control.
Send Questions, Comments, and Suggestions to bencr@hotmail.com