فصلنامه هوش محاسباتی در مهندسی برق
سال پنجم شماره 4 (زمستان 1393)

Despite the high potential of distributed and renewable sources، their operation may cause problems because of their variability. Moreover، wind fluctuations or extreme weather changes may lead to temporary voltage fluctuations. Researches show that the energy storage can compensate this random nature effect and also it can be effective in a short duration، without requiring the load cut-off. Furthermore، utilizing the energy storing instruments provides more suitable conditions to use produced power and it can be considered as an economic solution. Therefore، in this paper a Smart Energy Management System has been designed in order to optimize the operation of a sample system، production planning، and energy storage. This study suggests the optimized method which can determine the optimized point depending on different goals and their relative effective coefficients. In this method، the usage time and the amount of usage of different energy sources have been determined so that the lowest cost and minimum environmental pollution has been achieved based on Pareto optimization. Eventually، in order to validate the proposed algorithm، this method has been implemented on an electrical propulsion sample system by MATLAB & GAMS software and related results are discussed.

In this paper a new strategy for congestion management is presented. Generally، in congestion management programs all considered contingencies are deterministic or stochastic. Therefore، congestion management cost is increased. In the proposed algorithm، congestion management program is divided to two parts، Primary and Secondary Congestion Management. Also، contingencies are divided in two groups. In the first group، the contingencies that should be managed by preventive actions are considered and the others are taken into account in the second group. The first group of contingencies is in primary congestion management. The secondary congestion management program starts from the nearest time to market run time. So، the secondary congestion management uses corrective actions for managing secondary group contingencies. Also، the secondary congestion management is capable of covering most uncertainties، especially load variations. The proposed method reduces congestion management cost.

The dynamic economic load dispatch is one of the main problems of power systems generation and operation. The objective is to schedule power generation for units over a certain period of time، while satisfying operating constraints and load demand in each interval. Wind farms، as renewable energy resources are playing an increasing role in electricity generation. In this paper، a computational framework is presented to solve the dynamic economic emission dispatch problem with inclusion of wind farms considering their associated constraints. An optimization algorithm called modified co-evolutionary particle swarm optimization (MCPSO) is proposed to solve the problem. In the proposed algorithm، two kinds of swarms evolve interactively where one of them is used to calculate the penalty factors (constraints handling) and the other is used for searching good solutions (optimization process). In addition، some modifications such as using an inertia weight that decreases linearly during the simulation are made to improve the performance of the algorithm. Finally، the validity and superiority of the proposed method are demonstrated by simulation results on a modified IEEE benchmark system including six thermal units and two wind farms.

Optimal operation and bidding strategy of renewable units are two important problems of the restructured power market. In this paper، a new method for the joint operation of wind، photovoltaic and pump-storage units in day ahead power market is studied to increase the profit of joint units. In this study، artificial neural network is used to predict the wind power generation of wind farms. Since، there are uncertainties in energy and reserve prices، wind and photovoltaic power generation، the optimal operation of joint units can be modeled as a stochastic optimization problem. For this purpose، uncertainties of parameters are modeled by scenario tree method. The performance of the proposed method is evaluated on the renewable energy resources (wind farms، photovoltaic and pump-storage units) of the modified IEEE 118 bus test system. Results of the proposed joint operation of renewable resources confirm that the value of expected profit increases in comparison with uncoordinated operation (UO) of units.

in this paper the optimal placement of spacers in surge arrester column is presented in order to achieve temperature reduction and surge arrester thermal stability against power losses due to the overvoltage in power system. The simulation is done by using genetic algorithm in MATLAB software that it is linked by numerical analysis، i. e.، Finite Element Method (FEM). First، electro thermal analysis is performed according to the IEC60099-4 standard on selected population in certain interval and، then the required data is applied to the genetic algorithm for the optimal placement of spacers. Simulation results show that the placement of spacers has great influence on surge arrester temperature variations. Finally، the optimal model of surge arrester is simulated in COMSOL software and the results of this model are compared with conventional model results.

energy resources، such as wind and solar، are increased. Also، the use of Electric Vehicles (EV) and Plug-in Hybrid Electric Vehicles (PHEV)، known as V2G، is under development. Due to the widespread use of these vehicles in the near future، Electric Vehicles Parking (EVP) is considered as a source of Distributed Generation (DG) and Electric Energy Storage. The location of parking lot is important for power utilities to reduce power losses، and to municipalities of the urban areas from construction point of view. In this paper، sitting of EVP considering GIS information and the extent of urban areas will be discussed for rapid determination of parking locations using different evolutionary algorithms. The goal is to reduce the candidate locations، to analyze and to compare the performance of these algorithms as well as increasing the satisfaction of power utilities and municipalities.

Nowadays، fields of music and artificial intelligence are closer together through research in both areas. Music composition using artificial intelligence (AI) solutions has created a challenging research area. Automatic music composition will not only help researchers understand human’s musical thinking، but also helps composers and musicians improve music theory significantly by using the computing power of computers. In this study، an automatic music composition is presented. The system is implemented by using Markov chain and Lindenmayer systems as well as genetic algorithm. Fitness evaluation of the generated music is achord-based. The evaluations show the fast evolution of the results by genetic algorithm using uniform mutation. Creativity in music composition is beyond the present borders of AI and much work is still ahead in this field.

In this paper، an intelligent islanding detection method is presented for inverter based distributed generation (DG) using probabilistic neural network (PNN) and wavelet transform. The presented method is based on the change of DG reactive power reference (Qref) in inverter control interface to create a small forced transient in frequency and its derivative. Changing the Qref causes a forced transient in system frequency and also in its derivative in islanding conditions. The main idea is to use the created transient in frequency derivative in islanding conditions. The PNN is trained by features extracted from the frequency derivative data through the discrete wavelet transformation (DWT) in islanding and non-islanding conditions. The proposed method is evaluated in islanding and non-islanding conditions، using PSCAD/EMTDC and MATLAB software. Simulation results show that the proposed method has a proper operation in the islanding and non-islanding conditions.