STREAMER 3.0: Towards Online Monitoring and Distributed Learning

Baudouin Naline (1) , Sandra Garcia-Rodriguez (1) , Karine Zeitouni (2)

1 LIIDE (CEA, LIST) - Laboratoire Instrumentation Intelligente Distribuée et Embarquée (CEA, LIST)
2 DAVID - Données et algorithmes pour une ville intelligente et durable - DAVID

Applications that generate continuous data have proliferated in recent years, and thus the challenge of processing those data streams has emerged. This requires Data Stream Processing frameworks with monitoring capabilities able to detect and react to any nondesired situation. Many streaming use cases deal with distributed sources of data which, for privacy and communication saving purposes, need to be tackled in a distributed manner. Based on the mentioned challenges, this paper presents STREAMER 3.0, an improvement on the former data stream framework with two new modules: (i) a monitoring manager with detection algorithms, alert raising and automatic model updater; and (ii) a distributed learning module relying on federated learning. We showcase these new functionalities with an example of remaining useful life estimation of turbofan engines using an LSTM.

Keywords: Streaming Framework; Data Stream; Distributed Machine Learning; LSTM; RUL Estimation; Federated Learning; artificial intelligence; distributed learning; machine learning; monitoring; anomaly detection; signal processing; Data Stream Processing

Domains: Artificial Intelligence [cs.AI]; Machine Learning [cs.LG]

Baudouin Naline, Sandra Garcia-Rodriguez, Karine Zeitouni. STREAMER 3.0: Towards Online Monitoring and Distributed Learning. CIKM '23: The 32nd ACM International Conference on Information and Knowledge Management, Oct 2023, Birmingham, United Kingdom. pp.5076-5080, ⟨10.1145/3583780.3614755⟩. ⟨hal-04263995⟩