ANN Based Approach for Nodal Congestion Pricing

In the deregulated scenario of power system the congestion management (CM), in a non-discriminatory open access transmission environment, is most crucial issue for power market operator. The associated pricing mechanism based on allocation of transmission capacity to determine nodal congestion prices (NCPs), plays a very important role in establishing an efficient CM procedure. In the emerging deregulated environment, the soft-computing based intelligent techniques like ANN provides a fast, accurate and efficient Nodal pricing, which ensures the successful trade in competitive spot power market This paper presents Levenberg Marquardt algorithm based multi-layer feed-forward neural network for providing NCPs in spot power market. Regarding congestion management the optimal pricing strategy breaks the nodal pricing into two components; one is locational marginal price (LMP) and second is nodal congestion price (NCP). In the present paper, the ANN is trained to provide NCPs at every node/bus for varying load condition. Since the training of ANN is extremely fast and test results are accurate, they can be directly floated to OASIS (open access same time information system) web site. The market participants willing to make transactions can access this information instantly. For proving the effectiveness of ANN, the results obtained after testing are compared with conventional IPM-OPF based method for a 6-bus test system having three generating units.

[1]  Tom Gedeon,et al.  A fuzzy-neural approach to electricity load and spot-price forecasting in a deregulated electricity market , 2003, TENCON 2003. Conference on Convergent Technologies for Asia-Pacific Region.

[2]  D K Smith,et al.  Numerical Optimization , 2001, J. Oper. Res. Soc..

[3]  Manjaree Pandit,et al.  Levenberg Marquardt algorithm based economic load dispatch , 2006, 2006 IEEE Power India Conference.

[4]  J. Stonham,et al.  Decomposition model and interior point methods for optimal spot pricing of electricity in deregulation environments , 2000 .

[5]  Manjaree Pandit,et al.  Voltage security assessment employing coherency-based feature selection for a neural network , 2004 .

[6]  Yuan-Kang Wu Comparison of Pricing Schemes of Several Deregulated Electricity Markets in the World , 2005, 2005 IEEE/PES Transmission & Distribution Conference & Exposition: Asia and Pacific.

[7]  M. K. Soni,et al.  Artificial neural network based peak load forecasting using Levenberg-Marquardt and quasi-Newton methods , 2002 .

[8]  Yochanan Shachmurove,et al.  Applying Artificial Neural Networks to Business, Economics and Finance , 2002 .

[9]  Laxmi Srivastava,et al.  Fast voltage contingency screening using radial basis function neural network , 2003 .

[10]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[11]  Ying-Yi Hong,et al.  A neuro-fuzzy price forecasting approach in deregulated electricity markets , 2005 .