فصلنامه هوش محاسباتی در مهندسی برق
سال دهم شماره 1 (بهار 1398)

In this paper, a new approach based on imperialist competitive algorithm (ICA) has been proposed to solve the combined heat and power economic dispatch (CHPED) problem. In order to avoid trapping in local optimum and improve the solution quality of the original ICA, a new assimilation policy has been addressed with varying coefficients during iterations. CHPED problem is a non-convex and non-linear optimization problem which has various constraints. Unlike previous methods, valve point effects are considered in some case studies and the effect of valve-point in cost function considered with adding an absolute sinusoidal term to conventional polynomial cost function. To evaluate the effectiveness of the proposed method, three different test cases with small, medium and large scales have been applied to investigate the performance of the proposed method on the CHPED problems. Each case study is including different test systems. Numerical results demonstrate the superiority of the proposed framework and reveal that MICA can find better solutions in comparing with the other methods.   Keywords:

Installing new energy sources as redundant black-start (BS) units is an efficient way to enhance the speed of power system restoration, especially when there is a high risk that the available power plants considered as BS units fail to operate. In this regard, this paper provides a new optimal design for the placement of the Gas Turbine (GT) as the redundant energy source to improve the power system performance during both restoration and normal conditions. In doing so, there will be contradictory objective functions to be minimized. Therefore, a multi-objective problem (MOP), as a mixed integer linear programming (MILP), is defined. The Pareto optimal solutions of the MOP are obtained by using a new population-based meta-heuristic technique, called Crow Search Algorithm (CSA). Two power systems are used for the validation of the proposed method. The simulation results show that the system can benefit from this method not only to increase the capability of black-start generation, but also to improve the power system performance in normal conditions. During the restoration process, it also provides the optimal start-up sequences of non-black-start (NBS) units with the optimal transmission paths.

Short term load forecasting is one of the key components for economical and safe operation of power systems. In competitive environment of electricity market, electricity utilities require more accurate load forecasting strategies to make better decisions on purchasing or generating electricity. This article offers a new method based on machine learning short-term load forecasting which is made up of a two-level feature selection technique and a new forecast engine. The feature selection part uses irrelevancy and redundancy filters to select best sets of input features. The proposed forecast engine is composed of a support vector regression machine, hybrid neural network and comprehensive learning particle swarm optimization. By applying comprehensive learning particle swarm optimization along with hybrid neural networks, the accuracy of forecasting is improved and its error decreases effectively.The proposed strategy is tested on PJM and AEMO electricity markets. The numerical results show the effectiveness and robustness of this method in comparison with recent short-term load forecasting methods.

In this paper, a new method based on Adaptive Neuro-Fuzzy Inference System (ANFIS) is proposed for locating the switched capacitor banks in distribution systems. To train the proposed ANFIS model, an index based on current transient is introduced, which is calculated either offline by using data or online by real time simulation. The proposed method uses only current transient waveforms, immediately before and after the switching instant. Since only the current signal is used which is available in several locations, the method is simple and can be applied online. The method uses wavelet to determine the capacitor switching instant, which is needed for the ANFIS model to locate the switching capacitor. The method is simulated using PSCAD. Through various simulations, it is shown that other power quality disturbances such as voltage dip, unbalances and harmonics cannot disturb the method. Moreover, the size and connection type of the capacitor bank do not affect the method accuracy. The proposed algorithm is validated by simulating the IEEE 13-bus distribution system. According to the simulation results, the method is reliable enough to be applied to real systems.

Low Voltage Ride Through (LVRT) capability is essential for wind farms to avoid disconnection during low voltage and fault. In this study, both Voltage Behind Reactance (VBR) model and DQ model of Induction Generators (IGs) used in Fixed Speed Wind Turbines (FSWTs) are implemented and compared. Based on the appropriate model, a new method for enhancing Low Voltage Ride Through (LVRT) capability of FSWTs during balanced three-phase faults is proposed. This method is based on using a Synchronous Condenser (SC) with a Fuzzy Logic Controller (FLC). In order to have a good control of the system during the fault, the amount of injected reactive power produced by the SC is controlled through the FLC. Although using STATCOM is the most common method for LVRT capability enhancement in FSWTs, simulation results show that using the SC with the FLC in a three-phase fault leads to a better performance. Therefore, using the VBR model for the first time in FSWTs and suggesting the application of the SC with the FLC to improve LVRT capability are the novelties of this paper.

In a competitive electricity market, an accurate short term price forecasting is essential for all the participants in market as a risk management technique.  For both spot markets and long-term contracts, price forecast is necessary to develop bidding strategies or negotiation skills in order to maximize benefit.  This paper proposes an efficient tool for short-term electricity price forecasting with a simple model and acceptable computation time by combining several intelligent methods.  Using inference, Adaptive Network-based Fuzzy Inference System (ANFIS) is used to determine the nonlinear relation between large quantities of input variables and forecasted price (output variable).  To decrease the complexity and improve the accuracy, mutual information (MI) technique is used to efficiently select the best set of input variables which have important information concerning forecasted price.  Moreover, Particle Swarm Optimization (PSO) algorithm with new strategy in choosing the particles is adopted to tune ANFIS parameters more precisely.  To evaluate the accuracy and performance, the proposed hybrid Mutual Information-ANFIS-PSO (MIAP) methodology is implemented on the real world case study of Spanish electricity market.  The results show the great potential of this proposed method in fast and accurate short-term price forecasting in comparison with some of the previous price forecasting techniques.