Data preprocessing using hybrid general regression neural networks and particle swarm optimization for remote terminal units

Data corruption in SCADA systems refers to errors that occur during acquisition, processing, or transmission, introducing unintended changes to the original data. In SCADA-based power systems, the data gathered by remote terminal units (RTUs) is subject to data corruption due to noise interference or lack of calibration. In this study, an effective approach based on the fusion of the general regression neural network (GRNN) and the particle swarm optimization (PSO) technique is employed to deal with errors in RTU data. The proposed hybrid model, denoted as GRNN-PSO, is able to handle noisy data in a fast speed, which makes it feasible for practical applications. Experimental results show the GRNN-PSO model has better performance in removing the unintended changes to the original data compared with existing methods.

[1]  Andries Petrus Engelbrecht,et al.  A Cooperative approach to particle swarm optimization , 2004, IEEE Transactions on Evolutionary Computation.

[2]  Chee Peng Lim,et al.  A hybrid neural network model for noisy data regression , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[3]  Mini S. Thomas,et al.  Intelligent algorithm for preprocessing multiple data at RTU , 2003 .

[4]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

[5]  Mini S. Thomas,et al.  Fuzzy-genetic algorithm for pre-processing data at the RTU , 2004 .

[6]  Yangmin Li,et al.  On Convergence and Parameter Selection of an Improved Particle Swarm Optimization , 2008 .

[7]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[8]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[9]  A.A. Najafi,et al.  Design a Real-Time Preprocessing Algorithm Based on a Co-evolutionary Fuzzy System , 2007, 2007 IEEE International Conference on Intelligent Computer Communication and Processing.

[10]  Kwanghee Nam,et al.  Faults diagnoses of rotating machines by using neural nets: GRNN and BPN , 1995, Proceedings of IECON '95 - 21st Annual Conference on IEEE Industrial Electronics.

[11]  Andries P. Engelbrecht,et al.  Computational Intelligence: An Introduction , 2002 .

[12]  Keshav P. Dahal,et al.  Intelligent Learning Algorithms for Active Vibration Control , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[13]  Xin Chen,et al.  A Modified PSO Structure Resulting in High Exploration Ability With Convergence Guaranteed , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[14]  Michael N. Vrahatis,et al.  Recent approaches to global optimization problems through Particle Swarm Optimization , 2002, Natural Computing.

[15]  J. Friedman.  Multivariate adaptive regression splines , 1990 .

[16]  A. G. Bruce.  Reliability analysis of electric utility SCADA systems , 1997 .

[17]  Xiao-Jun Zeng,et al.  Density-Driven Generalized Regression Neural Networks (DD-GRNN) for Function Approximation , 2007, IEEE Transactions on Neural Networks.

[18]  Maurice Clerc,et al.  The particle swarm - explosion, stability, and convergence in a multidimensional complex space , 2002, IEEE Trans. Evol. Comput..