Journal of Artificial Intelligence in Electrical Engineering
Volume:1 Issue: 2, Summer 2012

This paper describes the impact of the distance and the size of the corona ring, on the magnitude and distribution of electrical potential across the polymer insulators. The procedure is based on finite element method numerical analysis and stochastic optimization algorithm of differential evolution (DE). The optimal selection of corona ring has a significant impact on the control of potential and, consequently, on dielectric strengths, both inside and outside the insulator. This method is used for optimized determining of the size and the distance of corona ring from polymer insulators in existing structures.

In this article, a multi-objective function for placement of Distributed Generation (DG) and capacitors with the tap setting of Under Load Tap Changer (ULTC) Transformer is introduced. Most of the recent articles have paid less attention to DG, capacitor placement and ULTC effects in the distribution network simultaneously. In simulations, a comparison between different modes was carried out with, and without tap setting of ULTC. Simultaneous DG, capacitor placement, and ULTC transformer tap setting improve the voltage profile of load buses globally. In addition, they can also reduce loss and increase Available Transfer Capability (ATC). The IEEE 41-bus radial distribution network is used to illustrate the effectiveness and feasibility of the proposed approach.

This paper presents a novel method to calculate the reference source current and the reference compensating current for shunt active power filters (SAPFs). This method first calculates the amplitude and phase of the fundamental load current from a recursive algebraic approach block before calculating the displacement power factor. Next, the amplitude of the reference mains current is computed with the corresponding phase voltage. Finally, the difference between the actual load current and the reference source current is considered the reference compensating current to be delivered by the SAPF. The proposed method is presented and applied to the control system of the voltage source converter of SAPFs. The performance of the proposed method in reducing harmonics and improving the power factor is examined with a SAPF simulation model. The results are compared with the instantaneous active and reactive p-q power theory as other reference generation method.

Transmission network expansion planning (TNEP) is an important component of power system planning. It determines the characteristics and performance of the future electric power network and influences the power system operation directly. Different methods have been proposed for the solution of the static transmission network expansion planning (STNEP) problem till now. But in all of them, STNEP problem considering the network losses, voltage level and uncertainty in demand has not been solved by improved binary particle swarm optimization (IBPSO) algorithm. Binary particle swarm optimization (BPSO) is a new population-based intelligence algorithm and exhibits good performance on the solution of the large-scale and nonlinear optimization problems. However, it has been observed that standard BPSO algorithm has premature convergence when solving a complex optimization problem like STNEP. To resolve this problem, in this study, an IBPSO approach is proposed for the solution of the STNEP problem considering network losses, voltage level, and uncertainty in demand. The proposed algorithm has been tested on a real transmission network of the Azerbaijan regional electric company and compared with BPSO. The simulation results show that considering the losses even for transmission expansion planning of a network with low load growth is caused that operational costs decreases considerably and the network satisfies the requirement of delivering electric power more reliable to load centers. In addition, regarding the convergence curves of the two methods, it can be seen that precision of the proposed algorithm for the solution of the STNEP problem is more than BPSO.

In this paper, we present a new method to determine the optimal location and parameter settings of Unified Power Flow Controller (UPFC) for removing voltage violations and transmission lines overloading. UPFC is considered as the most powerful member of the FACTS devices, that it can control shunt and series power flow. This option gives to UPFC the power to control the voltage profile and transmission lines flow simultaneously. We used the Imperialistic Competitive Algorithm (ICA) to determine the optimal location and optimal parameter settings of UPFC to improve the performance of the power system specially removing voltage violations in the buses and solving transmission lines overloading to increase loadability in the power networks. This procedure is proposed to be applied on IEEE 14 bus system to show the validity of the method.

The main objective of this paper is to introduce a new intelligent optimization technique that uses a predictioncorrection strategy supported by a recurrent neural network for finding a near optimal solution of agiven objective function. Recently there have been attempts for using artificial neural networks (ANNs) in optimization problems and some types of ANNs such as Hopfield network and Boltzmann machine have been applied in combinatorial optimization problems. However, ANNs cannot optimize continuous functions and discrete problems should be mapped into the neural networks architecture. To overcome these shortages, we introduce anew procedure for stochastic optimization by a recurrent artificial neural network. The introduced neurooptimizer (NO) starts with an initial solution and adjusts its weights by a new heuristic and unsupervised rule to compute the best solution. Therefore, in each iteration, NO generates a new solution to reach the optimal or near optimal solutions. For comparison and detailed description, the introduced NO is compared to genetic algorithm and particle swarm optimization methods. Then, the proposed method is used to design the optimal controller parameters for a five bar linkage manipulator robot. The important characteristics of NO are: convergence to optimal or near optimal solutions, escaping from local minima, less function evaluation, high convergence rate and easy to implement.

This paper presents a method for damping of low frequency oscillations (LFO) in a power system. The power system contains static synchronous series compensators (SSSC) which using a chaotic harmony search algorithm (CHSA), optimizes the lead-lag damping stabilizer. In fact, the main target of this paper is optimization of selected gains with the time domain-based objective function, which is solved by chaotic harmony search algorithm. The performance of the proposed two-machine power system equipped with SSSC is evaluated under various disturbances and operating conditions and compared to power system stabilizer (PSS). The effectiveness of the proposed SSSC controller to damp out of oscillations, over a wide range of operating conditions and variation of system parameters is shown in simulation results and analysis.