P. Somasundaram, S.G. Bharathi Dasan, G. Sadasivam, K. Kuppusamy, and R.P. Kumudini Devi (India)
Artificial Intelligence Applications, Economic Dispatch, Hopfield model, piecewise quadratic cost function.
This paper presents the application of fast computation Hopfield neural network to economic dispatch (ED) of generators having piecewise quadratic cost functions. Traditionally a convex cost function for each generator is assumed. However, it is more realistic to represent the cost function as a piecewise quadratic function rather than single convex function. In this study, multiple intersecting cost functions are used for each unit. The modified Hopfield method employs a linear input-output model for neurons. Formulations for solving the ED problems are explored. This method determines the weight factors of the energy function by direct computation where as in the usual Hopfield methods weight factors are calculated by trial and error method. The solution to the ED problem is also obtained by direct computation. The effectiveness of this method is tested by applying it to a sample system. Computational results manifest that the method has a lot of excellent performances, and it is superior to other methods in many respects.
Important Links:
Go Back
