스마트미디어저널 (Smart Media Journal)

  • 제13권7호
  • /
  • Pages.9-17
  • /
  • 2024
  • /
  • 2287-1322(pISSN)
  • /
  • 2288-9671(eISSN)
한국스마트미디어학회 (THE KOREAN INSTITUTE OF SMART MEDIA)
권호 표지
DOI QR코드

DOI QR Code

이상 전력 탐지를 위한 TCN-USAD

TCN-USAD for Anomaly Power Detection

  • 진현석 (전남대학교 인공지능융합학과) ;
  • 김경백 (전남대학교 인공지능융합학과)
  • 투고 : 2024.06.15
  • 심사 : 2024.07.15
  • 발행 : 2024.07.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

에너지 사용량의 증가와 친환경 정책으로 인해 건물 에너지를 효율적으로 소비할 필요가 있으며, 이를 위해 딥러닝 기반 이상 전력 탐지가 수행되고 있다. 수집이 어려운 이상치 데이터의 특징으로 인해 Recurrent Neural Network(RNN) 기반 오토인코더를 활용한 복원 에러 기반으로 이상 탐지가 수행되고 있으나, 시계열 특징을 온전히 학습하는데 시간이 오래 걸리고 학습 데이터의 노이즈에 민감하다는 단점이 있다. 본 논문에서는 이러한 한계를 극복하기 위해 Temporal Convolutional Network(TCN)과 UnSupervised Anomaly Detection for multivariate time series(USAD)를 결합한 TCN-USAD를 제안한다. 제안된 모델은 TCN 기반 오토인코더와 두 개의 디코더와 적대적 학습을 사용하는 USAD 구조를 활용하여 빠르게 시계열 특징을 온전히 학습할 수 있고 강건한 이상 탐지가 가능하다. TCN-USAD의 성능을 입증하기 위해 2개의 건물 전력 사용량 데이터 세트를 사용하여 비교 실험을 수행한 결과, TCN 기반 오토인코더는 RNN 기반 오토 인코더 대비 빠르고 복원 성능이 우수하였으며, 이를 활용한 TCN-USAD는 다른 이상 탐지 모델 대비 약 20% 개선된 F1-Score를 달성하여 뛰어난 이상 탐지 성능을 보였다.

Due to the increase in energy consumption, and eco-friendly policies, there is a need for efficient energy consumption in buildings. Anomaly power detection based on deep learning are being used. Because of the difficulty in collecting anomaly data, anomaly detection is performed using reconstruction error with a Recurrent Neural Network(RNN) based autoencoder. However, there are some limitations such as the long time required to fully learn temporal features and its sensitivity to noise in the train data. To overcome these limitations, this paper proposes the TCN-USAD, combined with Temporal Convolution Network(TCN) and UnSupervised Anomaly Detection for multivariate data(USAD). The proposed model using TCN-based autoencoder and the USAD structure, which uses two decoders and adversarial training, to quickly learn temporal features and enable robust anomaly detection. To validate the performance of TCN-USAD, comparative experiments were performed using two building energy datasets. The results showed that the TCN-based autoencoder can perform faster and better reconstruction than RNN-based autoencoder. Furthermore, TCN-USAD achieved 20% improved F1-Score over other anomaly detection models, demonstrating excellent anomaly detection performance.

키워드

과제정보

이 논문은 정부(과학기술정보통신부)의 재원으로 정보통신기획 평가원의 지원을 받아 수행된 지역지능화혁신인재 잉성사업 임(IITP-2024-00156287, 50%) 본 연구는 과학기술정보통신부 및 정보통신기획 평가원의 인공지능융합혁신인재 양성사업 연구 결과로 수행되었음(IITP-2023-RS-2023-00256629, 50%)

참고문헌

  1. Global energy consumption driven by more electricity in residential, commercial buildings (2019), https://www.eia.gov/todayinenergy/detail.php?id=41753 (accessed Jun., 1, 2024).
  2. Shaikh, Pervez Hameed, et al. "A review on optimized control systems for building energy and comfort management of smart sustainable buildings," Renewable and Sustainable Energy Reviews, vol. 34, pp. 409-429, 2014.
  3. Pipattanasomporn, Manisa, et al. "CU-BEMS, smart building electricity consumtion and indoor environmental sensor datasets," Scientific Data, 7.1(2020): 241.
  4. Choi, Kukjin, et al. "Deep learning for anomaly detection in time-series data: Review, analysis, and guidelines," IEEE acces, vol. 9, pp. 120043-120065.
  5. Zhang, Chuxu, et al. "A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time series data," Proceedings of the AAAI coherence on artificial intelligence, Vol. 3 3. no. 01. 2019.
  6. Basumallik, Sagnik, Rui Ma, and Sara Eftekhamejad. "Packet-data anomaly detection in PMU-based state estimator using convolutional neural network," International Journal of Electrical Power & Energy Systems, vol. 107, pp. 690-702, 2019.
  7. Hsieh, Ruei-Jie, Jerry Chou, and Chih-Hsiang Ho. "Unsupervised online anomaly detection on multivariate sensing time series data for smart manufacturing," 2019 IEEE 12th conference on service-oriented computing and applications (SOCA). IEEE, 2019.
  8. Choi, Yeji, et al. "Gan-based anomaly detection and localization of multivariate time series data for power plant," 2020 IEEE international conference on big data and smart computing (BigComp). IEEE, 2020.
  9. Audibert, Julien, et al. "Usad: Unsupervised anomaly detection on multivariate time series," Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, 2020.
  10. Bai, Shaojie, J. Zico Kolter, and Vladlen Koltun. "An empirical evaluation of generic convolutional and recurrent networks for sequence modeling." arXiv preprint arXiv:1803.01271 (2018).
  11. Zhang, Chuxu, et al. "A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time series data, " Proceedings of the AAAI conference on artificial intelligence, Vol. 33. No. 01. 2019.
  12. Hochreiter, Sepp, and Jurgen Schmidhuber. "Long short-term memory/' Neural computation, vol. 9, no. 8, pp. 1735-1780, 1997.
  13. Yeom, Sungwoong, Chulwoong Choi, and Kyung baek Kim. "LSTM-based collaborative source-side DDoS attack detection," IEEE Access, vol. 10, pp. 44033-44045, 2022.
  14. 류한일, et al. "충전 특성과 어텐션 기반 LSTM을 활용한 개선된 리튬이온 배터리 SOH 예측 모델," 스마트미디어저널, 제12권, 제11호, 103-112쪽, 2023년
  15. 김휘수, 정송헌, and 김경백, "어텐션 기반 협업형 소스측 분산 서비스 거부 공격 탐지," 정보처리학회 논문지 (KTSDE), 제13권, 제4호, 157-165쪽, 2024년
  16. Chung, Junyoung, et al. "Empirical evaluation of gated recurrent neural networks on sequence modeling," arXiv preprint arXiv:1412.3555 (2014).
  17. Gopali, Saroj, et al. "A comparison of TCN and LSTM models in detecting anomalies in time series data, " 2021 IEEE International Conference on Big Data (Big Data). IEEE, 2021.
  18. He, Yangdong, and Jiabao Zhao. ''Temporal convolutional networks for anomaly detection in time series," Journal of Physics: Conference Series, Vol. 1213. No. 4. IOP Publishing, 2019.
  19. Thill, Markus, et al. "Temporal convolutional autoencoder for unsupervised anomaly detection in time series," Applied Soft Computing, vol. 112, 107751, 2021.
  20. Mo, Ronghong, et al. "Unsupervised TCN-AE-based outlier detection for time series with seasonality and trend for cellular networks/7 IEEE Transactions on Wireless Communications, vol. 2, no. 5, pp. 3114-3127, 2022.
  21. Yu, Ling-rui, Qiu-hong Lu, and Yang Xue. "DTAAD: Dual TCN-attention networks for anomaly detection in multivariate time series data," Knowledge-Based Systems, vol. 295, 111849, 2014.
  22. Lin, Shuyu, et al. "Anomaly detection for time series using vae-lstm hybrid model," ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Ieee, 2020.
  23. Zhang, Kexin, et al. ''Self-supervised learning for time series analysis: Taxonomy, progress, and Prospects," IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024.
  24. Baldi, Pierre. "Autoencoders, unsupervised learning, and deep architectures/' Proceedings of ICML workshop on unsupervised and transfer learning. JMLR Workshop and Conference Proceedings, 2012.
  25. Goodfellow, Ian, et al. "Generative adversarial nets, " Advances in neural information processing systems 27, 2014.
  26. 전남대학교 건물별 전기사용량 (2021), https://sisul.jnu.ac.kr/sisul/13422/subview.do (accessed Jun„ 11, 2024).
  27. 공공데이터포털 광주시 일별 시간대별 전력거래량 (2023), https://www.data.go.kr/data/15104326/fileData.do (accessed Jun., 11, 2024).
  28. Gulati, Manoj, and Pandarasamy Arjunan. "LEAD1. 0: a large-scale annotated dataset for energy anomaly detection in commercial buildings," Proceedings of the thirteenth ACM international conference on future energy systems, 2022.
  29. 이윤기, et al. "SDN 을 위한 샘플링 기반 네트워크 플러딩 공격 탐지/방어 시스템," 스마트미디어 저널, 제4권, 제4호, 24-32쪽, 2015년
  30. 김구민, 정송헌, and 김경백, "개방형 정책 에이전트 기반 다자간 마이크로서비스 접근제어 정책," 스마트미디어저널, 제12권, 제9호, 60-71쪽, 2023년