Hybrid neuro-fuzzy system for power generation control with environmental constraints

• Published in: Energy conversion and management Vol. 49; no. 11; pp. 2997 - 3005
• Main Authors: Chaturvedi, Krishna Teerth, Pandit, Manjaree, Srivastava, Laxmi
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01.11.2008; Elsevier
• Subjects: Applied sciences; Artificial intelligence; Combined environmental economic dispatch (CEED); Economic data; Economics; Electric energy; Electric power generation; Emissions; Energy; Energy economics; Environmental economics; Environmental protection; Exact sciences and technology; Fuels; Gaussian membership functions; General, economic and professional studies; Government regulations; hybrids; Lambda iteration method; Levenberg–Marquardt algorithm; Linguistic categories; Methodology. Modelling; neural networks; operating costs; Price penalty factor; Q1; Combined environmental economic dispatch (CEED); Linguistic categories; Lambda iteration method; Levenberg–Marquardt algorithm; Gaussian membership functions; Price penalty factor; Demand; Uncertainty; Fuzzy system; Energy cost; Pollution control; Pollution prevention; Economic optimization; Iterative method; Neural network; Algorithm; Penalty method; Constrained optimization; Electricity; Optimal allocation; Price; Production capacity; Electric power production; Cost lowering; Levenberg-Marquardt algorithm
• ISSN: 0196-8904; 1879-2227
• DOI: 10.1016/j.enconman.2008.06.028

The real time controls at the central energy management centre in a power system, continuously track the load changes and endeavor to match the total power demand with total generation in such a manner that the operating cost is least. However due to the strict government regulations on environmental protection, operation at minimum cost is no longer the only criterion for dispatching electrical power. The idea behind the environmentally constrained combined economic dispatch formulation is to estimate the optimal generation allocation to generating units in such a manner that fuel cost and harmful emission levels are both simultaneously minimized for a given load demand. Conventional optimization techniques are cumbersome for such complex optimization tasks and are not suitable for on-line use due to increased computational burden. This paper proposes a neuro-fuzzy power dispatch method where the uncertainty involved with power demand is modeled as a fuzzy variable. Then Levenberg–Marquardt neural network (LMNN) is used to evaluate the optimal generation schedules. This model trains almost hundred times faster that the popular BP neural network. The proposed method has been tested on two test systems and found to be suitable for on-line combined environmental economic dispatch.