Novel AI approaches in power systems

The electric utility industry has been subjected to rapid deregulatory reforms which have lead to a significant increase in the complexity of the system from the viewpoint of management and control. In this context, traditional artificial intelligence (AI) approaches are no longer as accurate as we would like them to be. Hence, a new set of paradigms are required to take into account the increasing complexity. Firstly, more accurate load forecasting tools are required and we discuss recurrent neural networks (RNNs), hybrid neurofuzzy designs and modular neural networks as the emerging alternatives to the traditional feedforward networks. We then deal with the paradigm of neurofuzzy anticipatory systems, with application to power system control. We also discuss applications of "intelligent agents" to the areas of power system management and power trading in competitive markets.

[1]  M. Knapik,et al.  Developing intelligent agents for distributed systems: exploring architecture, technologies, & applications , 1998 .

[2]  Sung-Suk Kim.  Time-delay recurrent neural network for temporal correlations and prediction , 1998, Neurocomputing.

[3]  Alireza Khotanzad,et al.  ANNSTLF-Artificial Neural Network Short-Term Load Forecaster- generation three , 1998 .

[4]  C. L. McCullough.  Neural net control vs. anticipatory fuzzy control for a flexible beam: a comparison , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[5]  Ah Chung Tsoi,et al.  Discrete time recurrent neural network architectures: A unifying review , 1997, Neurocomputing.

[6]  Ah Chung Tsoi,et al.  Locally recurrent globally feedforward networks: a critical review of architectures , 1994, IEEE Trans. Neural Networks.

[7]  Man-Wai Mak,et al.  On the improvement of the real time recurrent learning algorithm for recurrent neural networks , 1999, Neurocomputing.

[8]  C.L. McCullough.  Laissez-faire anticipatory fuzzy control , 1996, Proceedings of 35th IEEE Conference on Decision and Control.

[9]  V. C. Ramesh,et al.  Intelligent agents for negotiations in market games. 2. Application , 1998 .

[10]  A. C. Liew,et al.  Fuzzy neural network and fuzzy expert system for load forecasting , 1996 .

[11]  A. C. Liew,et al.  Anticipatory fuzzy control of power systems , 1995 .

[12]  A. C. Liew,et al.  Demand forecasting using fuzzy neural computation, with special emphasis on weekend and public holiday forecasting , 1995 .

[13]  Yusuf Al-Turki,et al.  A comparative study of medium-weather-dependent load forecasting using enhanced artificial/fuzzy neural network and statistical techniques , 1998, Neurocomputing.

[14]  Lefteri H. Tsoukalas,et al.  Neurofuzzy approaches to anticipation: a new paradigm for intelligent systems , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[15]  Lefteri H. Tsoukalas,et al.  A neurofuzzy approach for the anticipatory control of complex systems , 1996, Proceedings of IEEE 5th International Fuzzy Systems.

[16]  Dipti Srinivasan,et al.  Evolving artificial neural networks for short term load forecasting , 1998, Neurocomputing.

[17]  Saifur Rahman,et al.  Peak load forecasting using a fuzzy neural network , 1995 .

[18]  Bahman Kermanshahi,et al.  Recurrent neural network for forecasting next 10 years loads of nine Japanese utilities , 1998, Neurocomputing.

[19]  Saifur Rahman,et al.  Fuzzy neural networks for time-series forecasting of electric load , 1995 .

[20]  Alireza Khotanzad,et al.  An adaptive and modular recurrent neural network based power system load forecaster , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[21]  J. Vermaak,et al.  Recurrent neural networks for short-term load forecasting , 1998 .

[22]  O. Uluyol,et al.  Local output gamma feedback neural network , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[23]  Dominic Maratukulam,et al.  ANNSTLF-a neural-network-based electric load forecasting system , 1997, IEEE Trans. Neural Networks.

[24]  Claire L. McCullough.  Intelligent Controllers which can Adapt to Changing Environments: Anticipatory Neuro-Fuzzy Control , 1993, 1993 American Control Conference.

[25]  Lefteri H. Tsoukalas,et al.  Fuzzy and neural approaches in engineering , 1997 .

[26]  Jenq-Neng Hwang,et al.  Real time recurrent neural networks for time series prediction and confidence estimation , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[27]  Alireza Khotanzad,et al.  An adaptive recurrent neural network system for multi-step-ahead hourly prediction of power system loads , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[28]  A. M. Wildberger.  Overview of exploratory research in soft computing applications to power systems at the Electric Power Research Institute , 1995, 1995 IEEE International Conference on Systems, Man and Cybernetics. Intelligent Systems for the 21st Century.

[29]  Les E. Atlas,et al.  Recurrent neural networks and robust time series prediction , 1994, IEEE Trans. Neural Networks.

[30]  V. C. Ramesh,et al.  Intelligent agents for negotiations in market games. I. Model , 1998 .