딥러닝 기반 비침입 부하 모니터링 프레임워크에서의 LSTNet 응용 = An Application of LSTNet in Deep Learning-based Non-intrusive Load Monitoring Framework

다국어 초록 (Multilingual Abstract)

In this study, a process of measuring and preprocessing power data for 4 types of home appliances and a deep training-based NILM technique were proposed. Active power of 4 types of home appliances (refrigerator, induction, TV, washer) was measured for about 3 weeks. The power data of each home appliance was measured to be aggregated in a smart meter. In order to disaggregate energy using LSTNet, four types of home appliances and smart meter power data were constructed as a training dataset. In the training process, we performed a parametric study to extract the optimal hyperparameter with the highest validation accuracy metric among the major parameters of LSTNet to verify the feasibility of NILM application of LSTNet.

참고문헌 (Reference)

1 김임규, "다수 가전기기 유효전력의 스팩토그램 분석 및 LSTM기반의 전력 분해 알고리즘" 한국융합학회 12 (12): 21-28, 2021

2 Murray, D., "Transferability of neural network approaches for low-rate energy disaggregation" 8330-8334, 2019

3 Ibrahim, M., "Smart sustainable cities roadmap : Readiness for transformation towards urban sustainability" 37 : 530-540, 2018

4 Janik, A., "Scientific landscape of smart and sustainable cities literature : A bibliometric analysis" 12 (12): 779-, 2020

5 Butterworth, S., "On the theory of filter amplifiers" 7 (7): 536-541, 1930

6 Hart, G. W., "Nonintrusive appliance load monitoring" 80 (80): 1870-1891, 1992

7 Çavdar, İ.H, "New design of a supervised energy disaggregation model based on the deep neural network for a smart grid" 12 (12): 1217-, 2019

8 Lai, G., "Modeling long-and short-term temporal patterns with deep neural networks" 95-104, 2018

9 Bonfigli, R., "Machine training approaches to non-intrusive load monitoring" Springer 31-90, 2020

10 Hazas, M., "Look back before leaping forward : Four decades of domestic energy inquiry" 10 (10): 13-19, 2011

11 Hochreiter, S., "Long short-term memory" 9 (9): 1735-1780, 1997

12 Armel, K. C., "Is disaggregation the holy grail of energy efficiency? The case of electricity" 52 : 213-234, 2013

13 Bilski, P., "Generalized algorithm for the non-intrusive identification of electrical appliances in the household" 2 : 730-735, 2017

14 Gopinath, R., "Energy management using non-intrusive load monitoring techniques-state-of-the-art and future research directions" 62 : 102411-, 2020

15 Schirmer, P. A., "Energy disaggregation using two-stage fusion of binary device detectors" 13 (13): 2148-, 2020

16 Chung, J., "Empirical evaluation of gated recurrent neural networks on sequence modeling"

17 Kim, Y., "Electrical event identification technique for monitoring home appliance load using load signatures" 296-297, 2014

18 Garcia, F. C. C., "Development of an intelligent system for smart home energy disaggregation using stacked denoising autoencoders" 105 : 248-255, 2017

19 Huovila, P., "Buildings and climate change: Status, challenges, and opportunities"

20 Salem, H., "Artificial Intelligence Techniques for a Scalable Energy Transition" Springer 109-131, 2020

21 Assan, T., "An empirical investigation of VI trajectory based load signatures for non-intrusive load monitoring" 5 (5): 870-878, 2013

22 Elma, O., "A survey of a residential load profile for demand side management systems" 85-89, 2017

23 Kolter, J. Z., "A public data set for energy disaggregation research" 25 : 59-62, 2011