Abstract
Federated Learning (FL) can enable industrial devices to collaboratively learn a shared Machine Learning (ML) model while keeping all the training data on the device itself. The FL inherently solves the data privacy issues where as it also reduces the cloud data hosting cost and communication overhead. However, existing FL algorithms and frameworks are generically designed and not evaluated against the industrial applications. In case of industrial applications, the data generated from assets and machines are mostly non-independent and Identically Distributed (non-IID) which demands for an investigation and evaluation on the existing FL algorithms against such non-IID industrial data. This paper presents a survey of FL frameworks, algorithms, and optimizers, and evaluates their performance against the industrial data. The paper shares the results of extensive numerical experiments conducted with the edge device, Raspberry pi. The data set used in this study is benchmarking fault classification industrial data, called PRONTO data set, for both IID and non-IID cases. With the experimental results, the paper demonstrates that the adaptive optimization-based FL algorithm, \(\texttt {FedAdam}\) outperforms other algorithms on an industrial time series fault classification application.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ge Z, Song Z, Ding SX, Huang B (2017) Data mining and analytics in the process industry: the role of machine learning. IEEE Access 5:20 590–20 616
Candanedo IS, Nieves EH, Gonzalez SR, Martın MTS, Briones AG (2018) Machine learning predictive model for industry 4.0. In: Uden L, Hadzima B, Ting I-H (2018) Knowledge management in organizations. Springer International Publishing, Cham, pp 501–510
Bagavathiappan S, Lahiri B, Saravanan T, Philip J, Jayakumar T (2013) Infrared thermography for condition monitoring-a review. Infrared Phys Technol 60:35–55
Abt S, Baier H (2014) Are we missing labels? a study of the availability of ground-truth in network security research. In: 2014 third international workshop on building analysis datasets and gathering experience returns for security (BADGERS). IEEE, pp 40–55
Diez-Olivan A, Del Ser J, Galar D, Sierra B (2019) Data fusion and machine learning for industrial prognosis: trends and perspectives towards industry 4.0. Inf Fusion 50:92–111
Moore ME, Ramage D, Hampson S, Arcas BAY (2017) Communication efficient learning of deep networks from decentralized data. In: -2017-Proceedings of the 20th international conference on artificial intelligence and statistics (AISTATS) 2017. PMLR, Fort Lauderdale, Florida, USA, pp 1273–1282. Accessed from 20–22 Apr 2017
Yang Q, Liu Y, Chen T, Tong Y (2019) Federated machine learning: concept and applications. ACM Trans Intell Syst Technol 10(2)
Nguyen V-D, Sharma SK, Vu TX, Chatzinotas S, Ottersten B (2021) Efficient federated learning algorithm for resource allocation in wireless IoT networks. IEEE Internet Things J 8(5):3394–3409
Hiessl T, Rezapour Lakani S, Kemnitz J, Schall D, Schulte S (2021) Cohort-based federated learning services for industrial collaboration on the edge
Hsu T-MH, Qi H, Brown M (2019) Measuring the effects of non-identical data distribution for federated visual classification. arXiv:1909.06335
Reddi SJ, Charles Z, Zaheer M, Garrett Z, Rush K, Konecný J, Kumar S, McMahan HB (2021)Adaptive federated optimization. In: ICLR
Li T, Sanjabi M (2020) Fair resource allocation in federated learning. In: ICLR
Li Q, Diao Y, Chen Q, He B (2021) Federated learning on non-iid data silos: an experimental study. arXiv:2102.02079
Aledhari M, Razzak R, Parizi RM, Saeed F (2020) Federated learning: a survey on enabling technologies, protocols, and applications. IEEE Access 8:140699–140725
Kholod I, Yanaki E, Fomichev D, Shalugin E, Novikova E, Filippov E, Nordlund M (2020) Open-source federated learning frameworks for IoT: a comparative review and analysis. Sensors 21(1):167
TensorFlow federated: machine learning on decentralized data. https://www.tensorflow.org/federated
Flower Framework. https://flower.dev/
Beutel DJ, Topal T, Mathur A, Qiu X, Parcollet T, Lane N (2020) Flower: a friendly federated learning research framework. vol. abs/ arXiv:2007.14390
Mathur A, Beutel Pedro Porto Buarque de Gusmao DJ, Fernandez-Marques J, Topal T, Qiu X, Parcollet T, Gao Y, Lane ND (2021) On-device federated learning with flower. arXiv:2104.03042v1 [cs.LG]
An industrial grade federated learning framework. https://fate.fedai.org
let’s solve privacy. https://blog.openmined.org/tag/pysyft/
Xaynet framework. https://www.xaynet.dev/
PRONTO heterogeneous benchmark data set. https://zenodo.org/record/1341583#.Yl0r3NpBw2w
Kairouz P, McMahan HB, Avent B, Bellet A, Bennis M, Bhagoji AN, Bonawitz K, Charles Z, Cormode G, Cummings R et al (2019) Advances and open problems in federated learning. arXiv:1912.04977
https://www.raspberrypi.com/products/raspberry-pi-4-model-b/
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Prathap Kumar, B., Chouksey, S., Amarlingam, M., Ashok, S. (2023). Evaluation of Federated Learning Strategies on Industrial Time Series Fault Classification. In: Chinara, S., Tripathy, A.K., Li, KC., Sahoo, J.P., Mishra, A.K. (eds) Advances in Distributed Computing and Machine Learning. Lecture Notes in Networks and Systems, vol 660. Springer, Singapore. https://doi.org/10.1007/978-981-99-1203-2_36
Download citation
DOI: https://doi.org/10.1007/978-981-99-1203-2_36
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1202-5
Online ISBN: 978-981-99-1203-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)