Optimal Scheduling of Thermal Power Generation Using Evolutionary Algorithms

The optimal scheduling of power generation is a major problem in Electricity generating industry. This scheduling problem is complex because of many constraints which can not be violated while finding optimal or near-optimal scheduling. A real-time scheduling of generating units involves the selection of units for for operation to meet the consumer requirement. These decisions are to be taken so as to minimize the sum of startup, banking and expected running costs subject to the demand and spinning_reserve, and satisfying the minimum down-time and up-time constraints of generating units. So the objective of the scheduling is to generate power to meet the load with minimum cost of generation. We tackled the problem with heuristic knowledge (load forecast) and genetic search technique. The paper examines the feasibility of using genetic algorithms, and reports results in determining a near-optimal commitment order of thermal units in a studied power system.

[1]  Bruce F. Wollenberg,et al.  A unit commitment expert system (power system control) , 1988 .

[2]  Lashon B. Booker,et al.  Intelligent Behavior as an Adaptation to the Task Environment , 1982 .

[3]  F.N. Lee,et al.  The Application of Commitment Utilization Factor (CUF) to Thermal Unit Commitment , 1991, IEEE Power Engineering Review.

[4]  P. G. Lowery,et al.  Generating Unit Commitment by Dynamic Programming , 1966 .

[5]  Md. Sayeed Salam,et al.  Integrating an expert system into a thermal unit-commitment algorithm , 1991 .

[6]  Arthur I. Cohen,et al.  A Branch-and-Bound Algorithm for Unit Commitment , 1983, IEEE Transactions on Power Apparatus and Systems.

[7]  S. M. Shahidehpour,et al.  A hybrid artificial neural network-dynamic programming approach to unit commitment , 1992 .

[8]  David E. Goldberg,et al.  Sizing Populations for Serial and Parallel Genetic Algorithms , 1989, ICGA.

[9]  Jonathan F. Bard,et al.  Short-Term Scheduling of Thermal-Electric Generators Using Lagrangian Relaxation , 1988, Oper. Res..

[10]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[11]  A. Merlin,et al.  A New Method for Unit Commitment at Electricite De France , 1983, IEEE Transactions on Power Apparatus and Systems.

[12]  S. M. Shahidehpour,et al.  An intelligent dynamic programming for unit commitment application , 1991 .

[13]  L. F. B. Baptistella,et al.  A Decomposition Approach to Problem of Unit Commitment Schedule for Hydrothermal Systems , 1980 .

[14]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[15]  Francisco D. Galiana,et al.  Towards a more rigorous and practical unit commitment by Lagrangian relaxation , 1988 .

[16]  John A. Muckstadt,et al.  An Application of Lagrangian Relaxation to Scheduling in Power-Generation Systems , 1977, Oper. Res..

[17]  Walter L. Snyder,et al.  Dynamic Programming Approach to Unit Commitment , 1987, IEEE Transactions on Power Systems.

[18]  C.K. Pang,et al.  Optimal short-term thermal unit commitment , 1976, IEEE Transactions on Power Apparatus and Systems.

[19]  S. M. Shahidehpour,et al.  A heuristic short-term unit commitment , 1991 .

[20]  Diego Arjona-Arguelles.  A hybrid artificial neural network , 1996 .

[21]  F. Albuyeh,et al.  Evaluation of Dynamic Programming Based Methods and Multiple area Representation for Thermal Unit Commitments , 1981, IEEE Transactions on Power Apparatus and Systems.

[22]  Francisco D. Galiana,et al.  Unit commitment by simulated annealing , 1990 .

[23]  W. J. Hobbs,et al.  An enhanced dynamic programming approach for unit commitment , 1988 .

[24]  Yuval Davidor,et al.  Epistasis Variance: Suitability of a Representation to Genetic Algorithms , 1990, Complex Syst..