Applied Mechanics and Materials Vol. 785

Abstract: The paper presents a comparison of Computational Intelligence techniques are Evolutionary Programming Swarm Optimization (EPSO), Particle Swarm Optimization (PSO), Evolutionary Programming (EP) to optimal placement and sizing of Static Var Compensator. The technique has been implemented to minimize the transmission loss and improve the voltage profile of the system. Simulation performed on standard IEEE 118-Bus RTS and indicated that EPSO a feasible to achieve the objective function.

Abstract: Distribution system as an important division of the electric power system as one of the most complicated systems created by the mankind. The problem of distribution system planning is to find the optimum location and sizing of the substation and the optimum feeder configuration to connect the consumers to the distribution substation and distribution substation to the primary substations. This paper proposes an algorithm to find the optimum distribution substation placement and sizing by utilizing the GA algorithm and optimum feeder routing using modified MST. The proposed algorithm has performed on distribution network model with 250 consumers form MV to LV levels. The result indicates that proposed algorithm is able to achieve the optimum number of substation in adequate placement and sizing with optimum feeder routing. The problem constraints of distribution network planning are considered as a part of objective function.

Abstract: Although, Back Propagation Neural Network are frequently implemented to forecast short-term electricity load, however, this training algorithm is criticized for its slow and improper convergence and poor generalization. There is a great need to explore the techniques that can overcome the above mentioned limitations to improve the forecast accuracy. In this paper, an improved BP neural network training algorithm is proposed that hybridizes simulated annealing and genetic algorithm (SA-GA). This hybrid approach leads to the integration of powerful local search capability of simulated annealing and near accurate global search performance of genetic algorithm. The proposed technique has shown better results in terms of load forecast accuracy and faster convergence. ISO New England data for the period of five years is employed to develop a case study that validates the efficacy of the proposed technique.

Abstract: This paper deals with the reconfiguration of the distribution network system to investigate the total power losses considering Distribution Generations (DGs) sizing concurrently. To overcome other limitations and enhance the solution performances, a new optimization approach called Improved Evolutionary Particle Swarm Optimization (IEPSO) is proposed. The primary aim of this study is to investigate the contribution of the proposed algorithms towards total power losses by considering the optimum DG size simultaneously. The proposed method is compared with the traditional Particle Swarm Optimization (PSO) and Improved Particle Swarm Optimization (IPSO) respectively. The amount of time that an algorithm spends in obtaining an alternative topological status for the system power loss reduction and distribution generation sizing is taken into consideration. In this context, the study is tested using IEEE 33 bus distribution system.

Abstract: Improper placement of capacitor as one of the compensating devices will lead to under-compensation or over-compensation which may lead to possible monetary losses. Thus optimization process has become a priori to address this problem. This paper presents cuckoo search algorithm in loss minimization via capacitor placement in distribution system. Implementation of sensitivity analysis for location identification; followed by optimal sizing determination via cuckoo search is a remarkable effort for the compensating scheme. Validation on a reliability test model, namely the IEEE 33-bus radial distribution system has indicated promising results. With the development of optimization engine, an attempt to assess its feasibility can be done through the implementation on larger test system. This is demonstrated by the simulation results, which revealed that cuckoo is feasible in ensuring loss has been minimized while maintaining voltage level within the acceptable range

Abstract: Power transformer has been identified as crucial and vital equipment in power system. Any disturbance such as faults will result in immense impact to the whole power system. This paper presents the development of an Evolutionary Programming (EP) – Taguchi Method (TM) – Artificial Neural Network (ANN) based technique for the classification of incipient faults in power transformer using Dissolved Gas Analysis (DGA) method based on historical industrial data. It involved the development of ANN model and embedding TM and EP as the optimization techniques in order to enhance the system accuracy and efficiency. ANN is a powerful computational technique that mimics how human brain process information. It has great ability to learn from experiences and examples, hence greatly suitable for classification, pattern recognition and forecasting purposes. In designing the ANN model, there are parameters which need to be chosen wisely. However, there is no systematic ways and guidelines to select the optimal ANN parameters. It is greatly dependent on the design knowledge and experiences of the experts. The process of finding suitable parameters is become difficult, tedious and time consuming, thus optimization technique is needed to overcome the shortcoming. In this study, TM and EP were employed as the optimization techniques to improve the ANN-based model. The findings obtained from the proposed technique have proved the effectiveness of both TM and EP in optimizing the ANN model. As a result, a reliable EP-TM-ANN based system has been successfully developed that can classify incipient faults in power transformer.

Abstract: This paper presents multi-objective optimization for sizing of distributed generation using cuckoo search algorithm. The study involved the development of cuckoo search optimization engine. Prior to the development of multi-objective for cuckoo algorithm, a pre-developed voltage stability index termed as FVSI for location identification is used in this study. Weighted sum technique is used as the fitness for the problem formulation. Objectives of the study are to minimize the total real power and improve its voltage stability condition. Test is done on IEEE 69-Bus Radial Distribution System. Results obtained from the study indicated that the proposed technique is feasible for further implementation in power system.

Abstract: —Network reconfiguration is a process of changing the original structure of the distribution network system with the intention of balancing the load in every system’s feeder at the same time to optimize the operation of the system. The process involve the changing of switching state (tie switches and sectionalize switches), with the aim to find the best combination that can increase the performance of the system while satisfying with the operational constraints. The extreme necessity to the process has become a challenging mission for the researcher to overcome the reconfiguration problems. Recent years have seen a rapid development of evolutionary algorithms and swarm intelligence based algorithms to resolve for network reconfiguration problems. For that reason, this report deals with Artificial Bee Colony (ABC) algorithm to be implemented in network reconfiguration procedure to achieve the optimum level of operation. The ease and simplicity of the algorithm and the capability to find the global optimization solution has made this algorithm appropriate for this project. The objective of this work focused on improvements of distribution power system, in terms of minimizing the total real power loss and improving the voltage profile within the acceptable value. The algorithm was tested on two different radial distribution system (33 bus and 69 bus radial distribution systems)

Abstract: This paper presents a new technique to predict the optimal amount of load to be shed at various loading conditions using Quantum-Inspired Evolutionary Programming–Support Vector Machine (QIEP-SVM). QIEP is utilised to optimise the RBF Kernel parameters in Least-Square Support Vector Machine (LS-SVM). The objective of the optimisation is to minimise the mean square error (MSE). The performance of QIEP-SVM technique was compared with those obtained from LS-SVM technique with prediction accuracy through a 10-fold cross-validation procedure. All simulations in this study were carried out using IEEE 69-bus distribution test system. QIEP-SVM model had shown better prediction performance as compared to LS-SVM. The results also indicate that the proposed approach outperforms the most recently reported technique in terms of accuracy and fast computation time.