Short Term Load Forecasting using Neuro-Fuzzy Approaches

B.K. Chauhan, A. Sharma, and M. Hanmandlu (India)


Electrical power system, short term electric load forecasting, artificial neural network, TSK fuzzy model, neuro-fuzzy hybrid system.


Electrical power system is considered to be one of the most complex systems in the world and for proper planning and management of such a system; knowledge of future load is a primary requisite. Various techniques, both traditional and modern, have been employed to predict the future load previously. This paper makes use of three approaches, the first being artificial neural network using back propagation algorithm (BP), second Takagi-Sugeno-Kang (TSK) fuzzy model and third neuro fuzzy hybrid system. The results obtained from all three approaches show the superiority of the neuro-fuzzy hybrid system over the other two. This case study has been performed on the load and weather data pertaining to the Neo pool region (New England) for the year 2003.

Important Links:

Go Back