Identification of Harmonic Source Location in Power Networks Using Neural Networks with Minimum Number of Measurement

Farajzadeh, R.; Khodaei, J.
October 2011
International Review on Modelling & Simulations;Oct2011, Vol. 4 Issue 5, p2324
Academic Journal
This paper presents a practical method for harmonic sources detection in a power network using neural network with sigmoid output layer and LVQ education algorithm. In some cases, to improve results, a consecutive BPN network has been used that in this paper is called CBPN. For comparison, the RBF neural network has been studied and results comparison shows that BPN is better. For optimum selection of numbers and locations of harmonic meters, Optimum line that is affected from harmonic sources and also system topology analysis method has been used. The applications of mentioned methods lead to obtain satisfactory results with the least number of harmonic meter and neural network input samples. When neural network is applied to harmonic sources detection, there are no knowledge about the existence of harmonic sources and their type. Using the state estimation method and optimization method such as genetic algorithm which are applied for the locating meter are confirmed, but these methods are so complicated and time consuming. The presented method in this paper is simple and also very precise. Other advantage of this paper is the proper selection of the neural network input parameters so that load and harmonic sources variations do not affect on the result considerably. Presented Method is tested on the IEEE-14 BUS network.


Related Articles

  • Reactive power tracing in pool-based power system utilising the hybrid genetic algorithm and least squares support vector machine. Mustafa, M.W.; Sulaiman, M.H.; Shareef, H.; Khalid, S.N. Abd. // IET Generation, Transmission & Distribution;Feb2012, Vol. 6 Issue 2, p133 

    This study presents a new method for reactive power tracing in a pool-based power system by introducing the hybrid genetic algorithm and least squares support vector machine (GA-LSSVM). The idea is to use GA to obtain the optimal values of regularisation parameter, γ, and kernel radial basis...

  • Optimal Parameter for the Training of Multilayer Perceptron Neural Networks by Using Hierarchical Genetic Algorithm. Orozco-Monteagudo, Maykel; Taboada-Crispi, Alberto; Gutiérrez-Hernández, Liliana // AIP Conference Proceedings;11/6/2008, Vol. 1060 Issue 1, p3 

    This paper deals with the controversial topic of the selection of the parameters of a genetic algorithm, in this case hierarchical, used for training of multilayer perceptron neural networks for the binary classification. The parameters to select are the crossover and mutation probabilities of...

  • Intelligent Classification of Three Phase Fault and Voltage Collapse for Correct Distance Relay Operation Using Support Vector Machine. Abidin, Ahmad Farid; Mohamed, Azah; Shareef, Hussain // International Review on Modelling & Simulations;Apr2012, Vol. 5 Issue 2, p623 

    The conventional techniques used in distance relay operation are not fast enough in distinguishing between a three phase fault and voltage collapse and this may lead to unintended tripping of protection devices. Therefore, there is a need for fast detection of voltage collapse so as to improve...

  • Combining Regression Estimators: Ga-Based Selective Neural Network Ensemble. Zhou, Zhi-Hua; Wu, Jian-Xin; Tang, Wei; Chen, Zhao-Qian // International Journal of Computational Intelligence & Applicatio;Dec2001, Vol. 1 Issue 4, p341 

    Neural network ensemble is a learning paradigm where a collection of neural networks is trained for the same task. In this paper, the relationship between the generalization ability of the neural network ensemble and the correlation of the individual neural networks constituting the ensemble is...

  • Forecasting of Wind Speed Using Artificial Neural Networks. Ramesh Babu, N.; Arulmozhivarman, P. // International Review on Modelling & Simulations;Oct2012, Vol. 5 Issue 5, p2276 

    Wind speed forecast is essential in wind energy conversion system and may fail to operate power plant at non optimal region if not properly forecasted. This paper focuses the short term wind speed forecasting using conventional statistical method and artificial neural networks such as back...

  • A Two-Stage Artificial Neural Network Classifier to Discriminate Three-Phase Unbalanced Voltage Sag Types. Deihimi, Ali; Momeni, Abolfazl // International Review on Modelling & Simulations;Oct2011, Vol. 4 Issue 5, p2305 

    This paper presents an efficient two-stage classifier based on artificial neural network (ANN) concept to discriminate different types of three-phase unbalanced voltage sags at the location of power quality monitoring. In the first stage, the general type of unbalanced voltage sag (C and D) in...

  • Recognition of Partial Discharge Pattern of Electrode Voids by Neural Network. Yanagisawa, Takashi; Iwamoto, Shinichi; Okamoto, Tatsuki; Fukagawa, Hiromasa // Electrical Engineering in Japan;4/1/1992, Vol. 112 Issue 2, p110 

    A back-propagation neural network model is used to identify electrode types involved in partial discharge (tree, IEC (b), CIGRE method I) and to estimate the shapes of the cylindrical electrode voids, based on the specific charge-phase characteristics of the different electrode types.

  • Voltage and Reactive Power Control Using Recurrent Neural Networks. Kojima, Yasuhiro; Izui, Yoshio; Kyomoto, Sumie; Goda, Tadahiro // Electrical Engineering in Japan;6/15/1994, Vol. 114 Issue 4, p119 

    Many controller using neural networks have been recently development. The hybrid and direct types are two major categories of such controllers. While the first type tunes the parameters of the conventional controller by means of neural networks, the latter constructs the controller by learning...

  • The Neural Network Method of Corrosion Diagnosis for Grounding Grid. Zai-En Hou; Fu-Jian Duan; Ke-Cun Zhang // AIP Conference Proceedings;11/6/2008, Vol. 1060 Issue 1, p353 

    Safety of persons, protection of equipment and continuity of power supply are the main objectives of the grounding system of a large electrical installation. For its accurate working status, it is essential to determine every branch resistance in the system. In this paper, we present a neural...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics