Application of Genetic Algorithm in Improvement of Efficiency of Neural Network

Goodarzi, Mahdi; Goudarzi, Mahmud
January 2012
Journal of Control Engineering & Technology;Jan2012, Vol. 2 Issue 1, p50
Academic Journal
In this article application of genetic algorithm is discussed in order to improve the response of MLP neural network method for forecasting consumed load peak. In this method genetic algorithm is used which has more power in finding total minimum in comparison with algorithms which are based on Newton. This method could find consumed load peak of west of Iran more precise than other models with MRE% (Mean relative error percent) equal 1.207. Several models of ANN with a hidden layer have been checked and the best of them was chosen as the best structure with 3 neutrons. Data scattering test was done in order to correct choosing of test, train and validation data and this matter confirmed correctness of choosing data collection. For guaranty the authority of outcomes of the model, ±40MW considered after checking graph as error span, in a way that real data will be followed.


Related Articles

  • A Hybrid Technique for Controlling Multi Line Transmission System Using Interline Power Flow Controller. Karthik, B.; Chandrasekar, S. // European Journal of Scientific Research;8/17/2011, Vol. 58 Issue 1, p59 

    Interline power flow controllers (IPFC) are commonly used for maintaining power flow in the multiline transmission lines and to increase the active power in the line. The main problem here is the identification of a proper place for fixing the IPFC in the transmission system. Here, we proposed a...

  • A Genetic Algorithm Approach for the Solution of Economic Load Dispatch Problem. Kumar, Naveen; Singh Parmar, K.P.; Dahiya, Surender // International Journal on Computer Science & Engineering;Jun2012, Vol. 4 Issue 6, p1063 

    This paper presents the application of Genetic algorithm (GA) to solve the economic load dispatch problem of the power system. The effectiveness of the proposed algorithm has been demonstrated on two different test systems considering the transmission losses. Test system-1 includes a three...

  • A Discrete-Event Neural Network Simulator for General Neuron Models. Makino, T. // Neural Computing & Applications;2003, Vol. 11 Issue 3/4, p210 

    Efficient simulation techniques for a discrete-event pulsed neural network simulator are developed. In a discrete-event simulation framework, simulation of complex neural behaviours, such as phase precession and phase arbitration, demands the prediction of delayed firing times. The new...

  • Modified Hopfield Neural Network Approach for Solving Nonlinear Algebraic Equations. Mishra, Deepak; Kalra, Prem K. // Engineering Letters;2007, Vol. 14 Issue 1, p135 

    In this paper, we present an neural network approach to solve a set of nonlinear equations. A modified Hopfield network has been developed to optimize a energy function. This approach provides faster convergence and extremely accurate solutions for all solvable systems. We solved and discussed...

  • Improved convergence order for augmented penalty algorithms. Dussault, Jean-Pierre // Computational Optimization & Applications;Dec2009, Vol. 44 Issue 3, p373 

    We refine the speed of convergence analysis for the quadratic augmented penalty algorithm. We improve the convergence order from 4/3 to 3/2 for the first order multiplier iteration. For the second order iteration, we generalize the analysis, and consider a primal–dual variant which...

  • NEURAL GENERALIZED PREDICTIVE CONTROL WITH REFERENCE CONTROL MODEL FOR AN INDUCTION MOTOR DRIVE. Merabet, A.; Ouhrouche, M.; Bui, R. T. // Control & Intelligent Systems;2008, Vol. 36 Issue 2, p144 

    In this paper the authors present a new advanced control algorithm for speed and flux tracking of an induction motor. This algorithm, called neural networks generalized predictive control (NGPC), uses a combination of artificial neural networks (ANN) and generalized predictive control (GPC)...

  • Artificial Neural Network Implementation for Maximum Power Point Tracking of Optimized Solar Panel. Sindhura, Lalam S.; Chaudhary, Kalpana // International Journal of Computer Applications;Sep2013, Vol. 78, p1 

    In this paper, maximum power point tracking of solar panel using artificial neural network control is developed and simulated in Mat lab. The Solar panel is modeled using conventional five parameter model and adjusted according to the manufacturer's datasheet values by calculating its internal...

  • A magnetic flux leakage analysis model based on finite element neural network. Yuan, Xichao; Wang, Changlong; Ji, Fengzhu; Zuo, Xianzhang // Insight: Non-Destructive Testing & Condition Monitoring;Sep2011, Vol. 53 Issue 9, p482 

    The major drawback of the finite element method (FEM), which is commonly used in magnetic leakage field testing, is the high cost of calculation. In this paper, a finite element neural network (FENN), which embeds a finite element model in a neural network structure, is adopted that enables a...

  • Enhancing Computational Thinking with Spreadsheet and Fractal Geometry: Part 2 Root-finding using Newton Method and Creation of Newton Fractals. Soman, K. P.; Manu Unni, V. G.; Krishnan, Praveen; Sowmya, V. // International Journal of Computer Applications;10/1/2012, Vol. 55, p9 

    This article shows how Newton's iterative methods for finding root of a polynomial equation can be used to create fractals in spreadsheets. Newton's method has served as one of the most fruitful paradigms in the development of complex iteration theory. The process of iteration is impossible to...


Read the Article


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

Try another library?
Sign out of this library

Other Topics