A Modified Ant Colony Optimization Algorithm for Power Scheduling
Vijo M Joy1, S. Krishnakumar2
1Vijo M. Joy, Department of Electronics, School of Technology and Applied Sciences, M G University Research Centre, Edappally, Kochi- 24, Kerala , India.
2S. Krishnakumar, Department of Electronics, School of Technology and Applied Sciences M G University Research Centre, Edappally, Kochi-24, Kerala , India.
Manuscript received on 25 August 2019. | Revised Manuscript received on 12 September 2019. | Manuscript published on 30 September 2019. | PP: 1083-1088 | Volume-8 Issue-11, September 2019. | Retrieval Number: J11750881019/2019©BEIESP | DOI: 10.35940/ijitee.J1175.0981119
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The purpose of this work is to solve the problems related to the power system in an efficient manner by assigning the optimal values. To meet the demand loads with good quality and quantity is a challenging problem in the field of the power system. Artificial Neural Network is realized in the field of energy management and load scheduling. The Backpropagation algorithm is used for the training purpose. It has the aspects of the quick meeting on the local bests but it gets stuck in local minima. To overcome this drawback an Ant Colony Optimization algorithm is presented to allocate optimal output values for the power system. This has the capacity for searching the global optimal solution. Present work modifies the ant colony optimization algorithm with backpropagation. This hybrid algorithm accelerates the network and improves its accuracy. The ant colony optimization algorithms provide an accurate optimal combination of weights and then use backpropagation technique to obtain the accurate optimal solution rapidly. The result shows that the present system is more efficient and effective. These algorithms significantly reduce the peak load and minimize the energy consumption cost.
Keywords: Load scheduling, Artificial Neural Network, Ant Colony Optimization, Backpropagation
Scope of the Article: