COMPUTATIONAL INTELLIGENCE IN ELECTRICAL ENGINEERING (INTELLIGENT SYSTEMS IN ELECTRICAL ENGINEERING)
Year:2016 | Volume:6 | Issue:4|Papers Count:8

Estimate the position of moving objects tracking is an important and Many algorithms have been proposed. In this paper, a method to estimate the position of moving objects by solving the Bayesian equations of nonlinear systems with non-Gaussian distributed algorithm based on particle filter are offered. In this way will build the first target model of weighted histogram, Then applying random noise in the location of the first frame image, predicted the candidate particles in the next step and build a histogram weighted by the candidate particles and particles Start by Bhattacharya distance weighting on the similarity between the target model and candidate model particles and estimated the target position in the next frame by the resampling algorithm in the particle filter, Finally an adaptive target model update is performed, if necessary, based on the best model for particle similar to the target.

In presence of wind units in the market and because of uncertainty related to wind power forecasting, market clearing will be done as a stochastic framework. The main advantage of the stochastic programming over its counterpart is that optimal decisions will be optimize expected value of the objective function. But despite this advantage in stochastic programming, the main drawback is the lack of consideration of other parameters indicating the probability distribution of the objective function which these parameters will be considered in context of the risk concept. In this paper, the problem of maximizing profit remaining of the joint energy and reserve market clearing for independent system operator and at the same time minimizing thermal units costs in presence of wind units and considering risk concept will be studied. The proposed model is a Mixed Integer Linear Programming (Model) along with Value at Risk (VaR) and Conditional Value at Risk (CVaR) risk measures in order to evaluating the operator risk-taking.

To control 3-DOF model of human arm movement in page and to reach robust control in external disturbance, unmodeled dynamics and uncertainties of model with time-varying properties, continues terminal sliding mode control as an adaptive-robust control was used. This controller have exponential convergence to zero tracing error, but chattering phenomenon in sliding control isn’t decrease desirable. In this paper, to decrease chattering, we coupled a recurrent neural network by a single hidden layer into the terminal sliding control (TSM). Moreover, because of systematic redundancy in the model of arm, don’t exist unique joint trajectories to considering as a default, so to reach online desired trajectories in reaching, online routing algorithm was used with Neuro-TSM control. For testing the robustness in control, we applied disturbance signals of torque. The results have shown,Neuro-TSM along with online routing algorithm, in addition to reducing chattering, could track joint trajectories and end effector path with very low errors.

In this paper, a fuzzy method called C-Means is used for division of a power system into different region. The extension of disturbance between these regions can be avoided by using a FACTS-embedded local controller in each region. Optimal location of FACTS devices (STATCOM) are determined by designing a voltage control method and using an optimization algorithm. This control method is a decentralized approach that prevents unallowable deviation of voltage during disturbances. To verify the performance of the proposed method, 118-bus IEEE power system is used. The simulation results show the desirable performance of the proposed method.

satellites as seen by the receiver(s), plays a very important role in the total positioning accuracy. Geometric Dilution of Precision (GDOP) is an indicator showing how well the constellation of GPS satellites is organized geometrically. The approach is based on approximation or classification of the GDOP factors utilizing the hybrid Particle Swarm Optimization (PSO) and Support Vector Machine (SVM) method. Without matrix inversion required, this method is capable of evaluating all subsets of satellites and hence reduces the computational burden. This would enable the use of a high-integrity navigation solution without the delay required for many matrix inversions. This method which are using the first time for classification of GDOP, were compared Neural Network (NN), Genetic Algorithm (GA), and SVM that recently been used for this purpose. The experiments show that the approximation total RMS errors of PSOSVM are less than 0.166m and total performance classification of PSOSVM is 99.9%.

HV substations equipment protection as a strategic point on the power network always has attracted attention of power planners. An increase in the generation capacity and interconnected operation of neighboring grids can result in an increase in the fault currents during a contingency in a power system. The increased fault currents may exceed the maximum fault current rating of existing protective apparatus. Therefore FCLs are used which perform switching operations quickly and safely in the event of a power system fault. This study proposes a methodology for determining the location of FCL by considering the reduction of fault current and the reliability indices according to the location of FCL in a conventional arrangement such as one breaker and half. Finally, the fuzzy decision method which is suitable for solving problems with no advantages respect to each other to determine the optimal location of FCLs is used.

In smart grids, customers will be enabled to change their strategies by electricity prices. In fact, in smart grid, we obvious a great correlation between price and load signals which show the market participants will have complex model in their decisions to maximize their profit. Many pervious-studies forecasted load or price independently. But they were not suitable for smart grid environment. To overcome this shortage, we present Multi-Input Multi-Output based Least Squares Support Vector Machine (MIMO-LSSVM) forecasted engine which can consider the correlation between price and load signals in simultaneous model. In other words, this paper presents a new hybrid algorithm to forecast day-ahead price and load in the electricity market. It consists of four stages known as a Discrete Wavelet Transform (DWT) to make valuable subsets, fuzzy mutual information (FMI) to select best input candidate and LSSVM-MIMO model. Finally, the LSSVM-MIMO parameters are optimized by a novel Improved Artificial Bee Colony (IABC) algorithm. Some forecasting indexes based on error factor are considered to shows the forecasting accuracy. Simulation results are examined on New England and New South Wales (NSW) Zone in Australia’s electricity markets. The numerical simulation results show that the proposed hybrid algorithm has good potential for forecasting simultaneous loap/price problems.

Simultaneous use of distributed generation units and sectionalizing switches, can significantly improves system reliability. Moreover, operation of these resources in distribution network can play important role in reducing power losses. In this paper, presents a method for simultaneous placement of mentioned equipments, in order to minimizing power loss and improving reliability with considering network technical constraints. For this problem, a cost based objective function is used. In proposed method, time varying aspect of loads is considered via multi level load modeling. An improved genetic based algorithm by introducing new and complementary operators is used as solution method for the mentioned optimal placement problem. The proposed method, based on improved genetic algorithm, is applied on a 33-bus IEEE radial distribution test system to demonstrate its performance and efficacy. Also the impact of considering time varying load model is investigated.