Adapting Internet of Things and Neural Network in Modelling Demand Side Energy Consumption and Management

Abstract

With the recent application of micro-grid system and off-grid renewable energy power system using internet of things (IoT) for the efficacy in demand side consumption management. The study employed usage of IoT supported with statistical initiative (logistic regression) to develop a knowledge-based solution for energy demand side consumption management. The research adopted two approaches to model the energy consumption pattern of a user with designed sensor nodes for environmental data acquisition (DAC) monitoring and state of switches (load points). Leveraging on Internet of Things, the sensor node network transferred synchronized the data collected to Google Firebase cloud storage in real time. The data collected were used to train a logistic regression model for the prediction states of the receptacles and sensor readings. The study further investigated power usage (user) against human presence and hour (period) of the day separately and a mathematical model of the relationship was developed. The results revealed customer’s energy consumption; this includes models for the future projection. The model can be deployed to predict energy management on the demand side efficiency and availability indices. The models could support energy management including receptacle automation prediction and wastage monitoring.

Keywords

• Electrical Energy
• Machine Learning
• MATLAB
• Sensor Node
• DAC

References

1. [1] E. Matallanas, M. Cagigail and A. Gutierrez, “Neural network controller for Active Demand-Side Management with PV energy in the residential sector,” Elsevier (Applied Energy), pp. 90-97, 2012.
2. [2] F.W. Yu, W.T. Ho, “Load allocation improvement for the chiller system in an institutional building using logistic regression,” Honk kong. Energy and Building, 201, pp. 10-18, 2019.
3. [3] M.Singha, “Load Forcasting Using Artificial Neural Network,” M.S. Thesis, Thapar Institute of Engineering and Technology, Punjab, India, 2018.
4. [4] A. D. Papalexopoulous, H. Shangyouand P, Tie-Mao, “An Implementation of a Neural Network Based Load Forecasting Model from the EMS,” IEEE Transaction on Power Systems, 9, pp. 1956-1962, 1994.
5. [5] C.N, Lu, H.T, Wu and A. Vemuri, “Neural Network Based Short Term Load Forecasting,” IEEE Transactions on Power System, vol. 8, pp. 336-342, 1993.
6. [6] L.S.Arthur, “Some Studies in Machine Learning Using the Game Checkers,” IBM Journal of Research and Development, 1959.
7. [7] R. Jose, H. Noriega and Wang, “A Direct Adaptive Neural-Network Control for Unknown Nonlinear Systems and Its Application,” IEEE Transaction on Neural Networks, 9, pp. 27-34, 1998.
8. [8] S.A.Kalogirou, “Artificial Neural Networks in Renewable Energy Systems Applications,” Renewable and Sustainable Energy Reviews, vol. 5, pp. 373-401, 2001.

9. [9] M. Alexandra, P. Marko, M. Porcius, C. Fortuna, and D. Mladenic, “Using Machine Learning on Sensor Data,” Journal of Computing and Information Technology, vol. 18, no. 4, 2010.
10. [10] T. Go, T. Moe, G. Hirotsugu, and N. Yuuichi, “Machine Learning Applied to Sensor Data Analysis,” Yokogawa Technical Report, vol. 59, no. 1, pp. 27-30, 2016.
11. [11] T. Mitchell, Machine Learning, Louisiana : McGraw Hill, 1997.
12. [12] C.K. Das, M. Sanaullah, H.M.G Sarower and M.M. Hassan, “Development of a Cell Phone Based Remote Control System: An Effective Switching System for Controlling Home and Office Appliances,” International Journal of Electrical and Computer Sciences, vol. 9, 2009.
13. [13] A.Z, Alkar and U. Buhur, “An Internet Based Wireless Home Automation System for Multifunctional Devices,” IEEE Transactions on Consumer Electronics, vol. 51, pp. 1169-1174, 2005.
14. [14] G. Song, F. Ding, W. Zhang and A.Song, “A Wireless Power Outlet System for Smart Homes,” IEEE Transactions on Consumer Electronics, vol. 54, pp. 1688-1691, 2008.
15. [15] C. Chen, S. Duan, T. Cai, B. Liu and G. Hu, “Smart Energy Management System for Optimal Microgrid Economic Operation,” IET Renewable Power Generation, vol. 5, 2010.
16. [16] T. Hiyama and K. Kitabayashi, “Neural Network Based Estimation of Maximum Power Generation from PV Module using Enviromental Information,” IEEE Transaction on Energy Conversion, vol. 12, pp. 241-247, 1997.
17. [17] H. Kim, Y. Ko and K.H. Jung, “Artificial Neural Network Based Feeder Reconfiguration for Loss Reduction in Distribution Systems,” IEEE Transactions on Power Delivery, vol. 8, pp. 1356-1366, 1993.
18. [18] K.J. Anil, M. Jianchang, and K.M., Mohiuddin., “Artificial Neural Networks: A Tutorial,” ACM Digital Library, vol 29 (3), pp. 31 – 44, 1996.