COMPUTATIONAL INTELLIGENCE IN ELECTRICAL ENGINEERING (INTELLIGENT SYSTEMS IN ELECTRICAL ENGINEERING)
Year:2014 | Volume:5 | Issue:3|Papers Count:8

Presenting proper and efficient energy management system (EMS) in the Microgrids (MG) is an important issue for gaining assurance to optimize energy usage based on price preference and system technical constraints. Nowadays by utilizing renewable energy resources and energy storage systems in MG, in addition to reducing the pollution caused by fossil fuels, the safety and power system reliability can also be improved. The proposed algorithm to implement an EMS shall increase the MG ability in both islanded and grid connected operating mode to supply non-responsive load demands from the economic points of view. Implementing EMS over the MG of Institute de Recerca on Energia de Catalunya (IREC) based on artificial bee colony (ABC) optimization approach to economic dispatch between various generation units, considering their offer price is main novelty of this paper. The obtained results from the proposed algorithm when compared with the EMS algorithm based on mixed integer non-linear programming (MINLP) demonstrate the reduction of about 18% of the total generation; and it also improves the efficiency of the demand/ generation side management.

There is a growing interest in the optimal design of the phase locked loops, because these circuits are widely used in communication and electronic circuits. Undoubtedly the most important objectives in designing PLLs (phase locked loops) are low power consumption and low delay. In this paper, the process of designing and the optimization of PFD (one of the main part in PLLs) are proposed by using particle swarm optimization (PSO) algorithm. In the proposed method, instead of carrying out the frequent experiments and simulations based on trial and error to achieve the desired parameters of the phase frequency detector, effective variables are sent to the PSO algorithm and optimization process is done by this algorithm. The results show a remarkable ability of this heuristic method to find transistors sizing for optimal power consumption and delay.

Temporal Pattern feature of a speech signal could be either extracted from the time domain or via their front-end vectors. This feature includes long-term information of variations in the connected speech units. In this paper, the second approach is followed, i.e. the features which are the cases of temporal computations, consisting of Spectral-based (LFBE) and Cepstrum-based (MFCC) feature vectors, are considered. To extract these features, we use posterior probability-based output of the proposed MTMLP neural networks. The combination of the temporal patterns, which represents the long-term dynamics of the speech signal, together with some traditional features, composed of the MFCC and its first and second derivatives are evaluated in an ASR task. It is shown that the use of such a combined feature vector results in the increase of the phoneme recognition accuracy by more than 1 percent regarding the results of the baseline system, which does not benefit from the long-term temporal patterns. In addition, it is shown that the use of extracted features by the proposed method gives robust recognition under different noise conditions (by 13 percent) and, therefore, the proposed method is a robust feature extraction method.

This paper investigates modeling, analysis and design of networked control systems (NCSs), which are of great interest due to the advantages presented here but also are technically complex because of the challenges of this class of systems such as delay and packet-dropout. Firstly, NCSs with packet dropouts are studied. Markov chains are introduced to describe historical behaviors of packet dropouts. By this method which introduced, general models are derived under single packet transmission protocols. Further more, controllers are designed to stabilizing the resulting closed-loop systems. Secondly, by above method an inverted pendulum which was controlled in a network with delays, is controlled in a network through packet-dropouts. simulation results show the effectiveness of the above method.

Medical imaging comprises different imaging modalities and processes to image human body for diagnostic and treatment purposes and, therefore has an important role in the improvement of public health in all population groups. In this paper, we present an intelligent hybrid noise reduction filter which is based on Neuro-Fuzzy systems. It is especially beneficial in medical image noise reduction. First stage we feed the input image into four general noise reduction filters in parallel. These general filters are: mean filter, median filter, weighted median filter and the adaptive median filter. At the second stage we give the output of the above filters as input into a Neuro-Fuzzy system. As expected, the ability of Neuro-Fuzzy systems in encoding human knowledge and using non-deterministic knowledge, allow us to achieve much more noise reduction from the input images. We implement the proposed method and use it for reduction of noise from a set of medical images affected with high noise density. Experimental results show that the idea is considerably effective.

In this paper, by presenting the asset management model, it is tried to investigate the importance of distributed generation (DG) unit placement from radial distribution system reliability indices sensitivity viewpoint and then DG placement will be carried out. Asset management model is designed and explained to maximize the benefit of distribution companies for invested capital. As the value of distribution system reliability indices depend on customers load pattern, any change in customers load pattern causes changes in distribution system reliability indices. One of the factors that changes customers load pattern, is load growth. With considering that the system hardware characteristics are being constant, the values of reliability indices are also highly dependent on load distribution. Therefore, for assessing the current studies the level of validity and the adequacy of system in future, current load distribution and load growth in future should be studied. In this paper, with optimal placement of DG, it is tried to minimize the distribution system reliability indices sensitivity in accordance with load growth in different load patterns.

The growing need of energy sources, especially in industrial countries and the shortage of the fossil resources cause a great concern in many countries. By considering the fact that the energy price is increased during the day, using the demand side management is getting more important. The major change in demand side management is the consideration of consumers'' responses to energy price variations. This paper investigates the effect of the demand response implementation on cost reduction in unit commitment considering wind power. Considering that the simultaneous implementation of unit commitment and the use of response programs would be a complex and nonlinear problem that contain continuous and discrete variable, the mixed integer programming is used. The proposed method is simulated in practical system and IEEE RTS 24-bus system and the results are analyzed.

In this paper a new approach using Teaching-Learning-Based Optimization (TLBO) is presented for the placement of Distributed Generators (DGs) in radial distribution systems in south of Kerman. In this approach a multiple objective planning framework is used to evaluate the impact of DG placement and sizing for an optimal development of the distribution system. In this study, the optimum sizes and locations of DG units are found by considering the power losses and voltage profile as variables into the objective function. The optimization process is done using the link between the Digsilent and Matlab. The results obtained show the improvement of the system in the presence of DGs.