A Constrained Satisfaction Model for Cost Minimization of Power System Generation

International Journal of Computer Science (IJCS) Published by SK Research Group of Companies (SKRGC)

Abstract

Constraint satisfaction is an Artificial Intelligence technique with wide applications in solving optimization problems. In this study, the concept of constraint satisfaction was used in the optimization of power system generation. The study adopted a qualitative research methodology. The data was gathered through secondary data collection method. Focus was on developing a model to provide an effective load distribution for optimal power generation with minimal fuel cost and satisfaction of the system constraints using deep belief network (DBN) with Relu Activation Function. Results obtained from the model show the optimal distribution of load as against equal distribution of load. The developed model recorded an accuracy level of 98%. The high level of accuracy shows the efficiency of deep belief network in the optimization of electricity generation in the power industry. The approach was validated using the Lagrangian Multiplier Method. The model was developed to assist operators in thermal power plants in the adequate planning and utilization of the various generating unit in order to generate power economically.

References

1. Abbasian, R., & Mouhoub, M. (2016). A new parallel ga-based method for constraint satisfaction problems. International Journal of Computational Intelligence and Applications 15, No. 03:1650017.

2. Alcaraz, J., & Concepción M (2011) "A robust genetic algorithm for resource allocation in project scheduling." Annals of operations Research 102, No. 1-4: 83-109.

3. Anireh, V.I.E., Ahiakwo, C.O., & Asagba, P.O. (2014). Cost Minimization of Power System Generation Using Artificial Neural Network (ANN). Afr J. of Comp & ICTs. Vol 7, No. 1. Pp49-58

4. Aydin D, Ozyon S., Yasar C, Liao T. (2014). Artificial bee colony algorithm with dynamic population size to combine economic and emission dispatch problem. Electrical Power and Energy Systems; 54:p. 144–153.

5. Bhattacharjee K, Bhattacharya A, Dey SH (2015). Backtracking search optimization based economic environmental power dispatch problems. Electrical Power and Energy Systems; 73: 830–842

6. Cai J., Ma X., Li Q., Li L., Peng H. (2010). A multi-objective chaotic ant swarm optimization for environmental/economic dispatch. Electrical Power and Energy Systems;, 32:p. 337–344.

7. Gandomi, A. H. (2014). Interior search algorithm (ISA): A novel approach for global optimization." ISA transactions 53, no. 4: 1168-1183.

8. Gao, L., Yin, L.J., Li, X.Y. (2017). A novel mathematical model and multi-objective method for the low-carbon flexible job shop scheduling problem, considering productivity, energy efficiency and noise reduction. Sustain Comput Infor 2017; 13: 15–30.

9. Goodfellow, I., Bengio, Y., Courville, A. (2016). Deep Learning. MIT Press

10. Gregor, K., Danihelka, I., Graves, A., Rezende, D. J., & Wierstra, D. (2015). DRAW: A Recurrent Neural Network For Image Generation. https://doi.org/10.1038/nature14236

11. Hadji B, Mahdad B, Srairi K, Mancer N. (2015). Multi-objective Economic Emission Dispatch Solution Using Dance Bee Colony with Dynamic Step Size. Energy Procedia; 2015, 74:p.65-76.

12. Jeddi B, Vahidinasab B. (2014). A modified harmony search method for environmental/economic load dispatch of real-world power systems. Energy Conversion and Management: pp.661–675.78

13. Kaur, M. &Singh, D. Fusion of medical images using deep belief networks. Cluster comput 23, 1439-1453 (2020). https://doi/10.1007/s10586-019-02999-x

14. Khan, A. I., & Al-Habsi, S. (2020). Machine Learning in Computer Vision. International Conference on Computational Intelligence and Data Science (ICCIDS 2019) (ICCIDS 2019). Procedia Computer Science 167 1444–1451/ 10.1016/j.procs.2020.03.355. Creative Commons: http://creativecommons.org/licenses/by-nc-nd/4.0

15. King, J. E., Jupe, S. C. E., and Taylorm P. C. (2015) Network State-Based Algorithm Selection for Power Flow Management Using Machine Learning. IEEE Transactions on Power Systems, vol. 30, no. 5, pp. 2657-2664.

16. Li, X., Gao, L., Pan, Q., Wan, L., & Chao, K.M. (2018). An Effective Hybrid Genetic Algorithm and Variable Neighborhood Search for Integrated Process Planning and Scheduling in a Packaging Machine Workshop: IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. (In-press), pp. (In-press). https://dx.doi.org/10.1109/TSMC.2018.2881686

17. Li, X.Y., Lu, C., Gao L. (2017). Energy-efficient permutation flow shop scheduling problem using a hybrid multiobjective backtracking search algorithm. J Clean Prod 2017; 144(144): 228–238.

18. Lu, Y., Zhou, J., Qin, H., Wang, Y., Zhang, L (2011). Environmental/economic dispatch problem of power system by using an enhanced multi-objective differential evolution algorithm. Energy Conversion and Management; 52:p.1175–1183.

19. Luo, G., Wen X., Li, H., Ming, W & Xie, G. (2017). An effective multi-objective genetic algorithm based on immune principle and external archive for multi-objective integrated process planning and scheduling,” Int. J. Adv. Manuf. Tech., vol. 91, pp. 3145-3158.

20. Mandal, K.K., Mandal, S., Bhattacharya, B., Chakraborty, N. (2015). Non-convex emission constrained economic dispatch using a new self-adaptive particle swarm optimization technique. Applied Soft Computing; 28:p. 188–195.

21. Miljkovic, Z., & Petrovic, M. (2017). Application of modified multi-objective particle swarm optimisation algorithm for flexible process planning problem. Int. J. Comput. Integr. Manuf., vol. 30, No. 2-3, pp. 271-291.

22. Oluwadare, S.A., Iwasokun, G.B., Olabode, O., Olusi, O. & Akinwonmi E.A (2016). Genetic Algorithm-based Cost Optimization Model for Power Economic Dispatch Problem. British Journal of Applied Science & Technology 15(6):1-10,2016, Article no.BJAST 24347. ISSN: 2231-0843, NLM ID:10166454

23. Patricia, T.L., Adriano A.F., Andre C.P. (2002). Application of genetic algorithms in the optimization of the operation planning of hydrothermal power systems. IEEE Transactions on Power Systems. 2002; 16(3):288-297.

24. Shanthi, V., Sridevi, G., Charanya, R., Josphin, J. M. (2020). Deep Belief Network (DBN) Classification for Lung Cancer Prediction using KNN Classifier. European Journal of Molecular & Clinical Medicine ISSN 2515-8260 Volume 07, Issue 09, 2020.

25. Shao, H., Jiang, H. & Zhang, X (2015). Rolling bearing fault diagnosis using an optimization deep belief network, Measurement Science ? Technology, vol. 26, no. 11, Article ID 115002, 2015.

26. Suman, M., Rao, M.V.G., Hnanumaiah, A., & Rajesh, K (2016). Solution of Economic Load Dispatch problem in Power System using Lambda Iteration and Back Propagation Neural Network Methods International Journal on Electrical Engineering and Informatics - Volume 8, Number 2, June 2016

27. Waiping, S., & Xueqiong Z. (2016). Signal reconstruction and bearing fault identification based on deep belief network. Electronic Design Engineering, vol. 24, no. 4, pp. 67–71, 2016.

28. Yang, Xin-She (2010). Nature-inspired metaheuristic algorithms. Luniver press.

29. Zhang, S. and Wong, T. N. (2018). Integrated process planning and scheduling: An enhanced ant colony optimization heuristic with parameter tuning,” J. Intell. Manuf., vol. 29, no. 3, pp. 585–601, Mar. 2018, doi: 10.1007/s10845-014-1023-3.

30. Zhang, B., Gu, B., Tian, G., Zhou, J., Huang, J., & Xiong, Y. (2018), Challenges and solutions of optical-based nondestructive quality inspection for robotic fruit and vegetable grading systems: A technical review." Trends in food science & technology 81: 213-231.

31. Zhang, L., Wong, T. (2015). An object-coding genetic algorithm for integrated process planning and scheduling,” Eur. J. Oper. Res., vol. 244, pp. 434-444, 2015.

Keywords

Constraint Satisfaction, Artificial Intelligence, Optimization, Cost Minimization power generation, Deep Belief Network