SimulationsThe algorithm for microgrid optimization using the Q-learning [8] reinforcement learningtechnique was developed in MATLAB for the purpose of simulating the electrical microgridoptimal performance. The goal is to optimize the power flow in the network using the Q-learningtechnique. The microgrid configuration includes an islanded mode of operation, with aphotovoltaic array as a renewable power source and a diesel generator as the conventional powersupplier. The battery storage is available as well as a dumping load. Cost per kW, batterycapacity, size of diesel generator, learning rate, among others can be mentioned as theparameters that might be modified to test the algorithm. Real datasets associated with solarradiation [9] and electrical
Dec. 2022.[7] Engine Power and Torque Curves. images.cdn.circlesix.co/image/still/uploads/posts/2016/08/58863cb65bd5ff6ed7edb03f4 1 9b51c6.gif.[8] Typical Electric Motor Torque & Power Curves. images.theconversation.com/files/269180/original/file-20190414-76843- 99pwbb.png?ixli b=rb-1.1.0&q=45&auto=format&w=754&fit=clip.[9] yashastronomy. "Arduino based RPM counter with a new and faster algorithm." Arduino Project Hub, 30 Apr. 2020, create.arduino.cc/projecthub/yashastronomy/arduino-based-rpm-counter-with-a-new- and- faster-algorithm-3af9f3.Appendix 1: Data Collection and Analysis [4]
fuel resources: A review and techno-economic analysis," Int J Hydrogen Energy. (2022). https://doi.org/10.1016/J.IJHYDENE.2022.08.202. 4. J.A. Okolie, E.I. Epelle, M.E. Tabat, U. Orivri, A.N. Amenaghawon, P.U. Okoye, B. Gunes, "Waste biomass valorization for the production of biofuels and value-added products: A comprehensive review of thermochemical, biological and integrated processes," Process Safety and Environmental Protection. 159 (2022) 323–344. https://doi.org/10.1016/J.PSEP.2021.12.049. 5. H. He, Q. Li, J. Tang, P. Liu, H. Zheng, F. Zhao, W. Guan, E. Guo, C. Xi, "Study of hydrogen generation from heavy oil gasification based on ramped temperature oxidation experiments," Int J Hydrogen Energy. 48
neural network," in Neural networks for perception, Academic Press, 1992, pp. 65-93.[14] Z. Zhang, "Improved adam optimizer for deep neural networks," in IEEE/ACM 26th International Symposium on Quality of Service (IWQoS), 2018.[15] A. Krizhevsky, I. Sutskeyer and G. E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," Communications of the ACM, vol. 60, no. 6, pp. 84-90, June 2017.[16] K. He, X. Zhang, S. Ren and J. Sun, "Deep Residual Learning for Image Recognition," in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016.[17] G. Huang, Z. Liu, M. Laurens Van Deer and K. Q. Weinberger, "Densely Connected Convolutional Networks," in 2017 IEEE