DOI QR코드

DOI QR Code

LSTM Model-based Prediction of the Variations in Load Power Data from Industrial Manufacturing Machines

  • Rita, Rijayanti (Department of Information and Communication Engineering, Changwon National University) ;
  • Kyohong, Jin (Department of Electronic Engineering, Changwon National University) ;
  • Mintae, Hwang (Department of Information and Communication Engineering, Changwon National University)
  • Received : 2022.10.12
  • Accepted : 2022.12.11
  • Published : 2022.12.31

Abstract

This paper contains the development of a smart power device designed to collect load power data from industrial manufacturing machines, predict future variations in load power data, and detect abnormal data in advance by applying a machine learning-based prediction algorithm. The proposed load power data prediction model is implemented using a Long Short-Term Memory (LSTM) algorithm with high accuracy and relatively low complexity. The Flask and REST API are used to provide prediction results to users in a graphical interface. In addition, we present the results of experiments conducted to evaluate the performance of the proposed approach, which show that our model exhibited the highest accuracy compared with Multilayer Perceptron (MLP), Random Forest (RF), and Support Vector Machine (SVM) models. Moreover, we expect our method's accuracy could be improved by further optimizing the hyperparameter values and training the model for a longer period of time using a larger amount of data.

Keywords

Acknowledgement

This work was supported by Gyeongnam SW Convergence Cluster 2.0 under the contract and the "Leaders in INdustry-university Cooperation +" Project by the Ministry of Education and National Research Foundation of Korea.

References

  1. D. Mao, K. Potty, and J. Wang, "The impact of power-electronics-based load dynamics on large-disturbance voltage stability," in Proceeding of IEEE Power & Energy Society General Meeting (PESGM), Portland: OR, USA, pp. 36-39, 2018. DOI: 10.1109/PESGM.2018.8586221.
  2. Y. Li, D. Han, and Z. Yan, "Long-term load forecasting based on data-driven linear clustering method," Journal of Power System and Automation, vol. 6, no. 2, pp. 306-316, Mar. 2018. DOI: 10.1007/s40565-017-0288-x.
  3. J. Hao, Y. Liu, H. Gu, D. Yang, R. Wang, J. Lei, M. Deng, and Z. Huang, "Short-term power load forecasting for larger consumer based on tensorflow deep learning framework and clustering-regression model," in Proceeding 2018 2nd IEEE Conference on Energy Internet and Energy System Integration (EI2), Beijing, China, pp. 1-6, 2018. DOI: 10.1109/EI2.2018.8582583.
  4. Z. Wang, J. Qin, and C. Cao, "Research on prediction of dynamic load complementary based on big data," in Proceedings of 2019 International Conference on Computer Network, Electronic and Automation (ICCNEA), Xian, China, pp. 369-373, 2019. DOI: 10.1109/ICCNEA.2019.00074.
  5. K. Zhou, Y. Zhou, and K. Deng, "A circular recursion algorithm power load forecasting model and application," in Proceedings of 2019 IEEE 3rd Conference on Energy Internet and Energy System Integration (EI2), Changsha, China, pp. 2870-2873, 2019. DOI: 10.1109/EI247390.2019.9061824.
  6. F. Kuang and D. Huang, "Power load prediction method based on VMD and dynamic adjustment BP," in Proceedings of 2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS), Xiamen, China, pp. 160-164, 2019. DOI: 10.1109/SAFEPROCESS45799.2019.9213431.
  7. A. Boltunov, S. Vasiliev, V. Karpenko, A. Voloshin, and E. Voloshin, "Short-term load forecasting system for smartgrids based on personal power units," in Proceedings of 2019 Modern Electric Power Systems (MEPS), Wroclaw, Poland, pp. 1-3, Sep. 2019. DOI: 10.1109/MEPS46793.2019.9394995.
  8. T. Gong and S. Tian, "Analysis and forecasting for power load of office building taking crowd behavior into account," in Proceeding of 2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC)), Chongqing, China, pp. 997-1000, 2019. DOI: 10.1109/ITAIC.2019.8785742.
  9. R. Rijayanti, A. B. Wahyutama, B. Lee, J. Kim, B. Yoo, and M. Hwang, "Design of smart devices and applications for managing the load power of industrial manufacturing machine," in Proceedings of The 17th International Conference on Multimedia Information Technology and Applications (MITA2021), Jeju, Korea, pp. 47-50, 2021.
  10. J. Schmidhuber. "Habilitation", Postdoctoral Thesis, The Technical University of Munich, Munich, 1993, [online] Available: https://people.idsia.ch/~juergen/onlinepub.html
  11. S. A. Ludwig, "Comparison of time series approaches applied to greenhouse gas analysis: ANFIS, RNN, and LSTM," in Proceeding of IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), New Orleans: NA, USA, pp. 1-6, 2019, DOI: 10.1109/FUZZ-IEEE.2019.8859013.
  12. C. Deb, F. Zhang, J. Yang, S. E. Lee, and K. W. Shah, "A review on time series forecasting techniques for building energy consumption," Renewable and Sustainable Energy Reviews, vol. 74, pp. 902-924, Jul. 2017. DOI: 10.1016/j.rser.2017.02.085.