On-Device Federated Learning for Remote Alpine Livestock Monitoring

Sabtain Ahmad; Thomas Schneidergruber; Ivona Brandic; Johannes Scholz

doi:10.1007/978-3-031-99857-7_26

On-Device Federated Learning for Remote Alpine Livestock Monitoring

Sabtain Ahmad
, Thomas Schneidergruber
, Ivona Brandic
, Johannes Scholz

Geoinformatics

Research output: Chapter in Book/Report/Conference proceeding/Legal commentary › Conference contribution › peer-review

Abstract

Alpine livestock monitoring is critical for ecological preservation and agricultural efficiency. However, existing solutions struggle with energy constraints, limited network availability, and intermittent connectivity in remote environments. To address this, we propose an on-device federated learning framework tailored for PV-powered IoT sensors to optimize energy-communication tradeoffs. Our approach introduces staleness-aware aggregation and solar-aware training scheduling to address intermittent connectivity and PV variability in remote alpine environments. Deployed on a real-world testbed with collar sensors, the framework achieves 92% accuracy in time-series location prediction and 89% F1-score in anomaly detection while using 68% less energy than centralized baselines.

Original language	English
Title of host publication	Euro-Par 2025
Subtitle of host publication	Parallel Processing - 31st European Conference on Parallel and Distributed Processing, Proceedings
Editors	Wolfgang E. Nagel, Diana Goehringer, Pedro C. Diniz
Publisher	Springer Nature Switzerland
Pages	365-379
Number of pages	15
ISBN (Print)	9783031998560
DOIs	https://doi.org/10.1007/978-3-031-99857-7_26
Publication status	Published - 2026

Publication series

Name	Lecture Notes in Computer Science

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Fields of Science and Technology Classification 2012

202 Electrical Engineering, Electronics, Information Engineering

Access to Document

10.1007/978-3-031-99857-7_26

Cite this

Ahmad, S., Schneidergruber, T., Brandic, I., & Scholz, J. (2026). On-Device Federated Learning for Remote Alpine Livestock Monitoring. In W. E. Nagel, D. Goehringer, & P. C. Diniz (Eds.), Euro-Par 2025: Parallel Processing - 31st European Conference on Parallel and Distributed Processing, Proceedings (pp. 365-379). (Lecture Notes in Computer Science). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-99857-7_26

Ahmad, Sabtain ; Schneidergruber, Thomas ; Brandic, Ivona et al. / On-Device Federated Learning for Remote Alpine Livestock Monitoring. Euro-Par 2025: Parallel Processing - 31st European Conference on Parallel and Distributed Processing, Proceedings. editor / Wolfgang E. Nagel ; Diana Goehringer ; Pedro C. Diniz. Springer Nature Switzerland, 2026. pp. 365-379 (Lecture Notes in Computer Science).

@inproceedings{4e594583671c4a549fd81a2bee112788,

title = "On-Device Federated Learning for Remote Alpine Livestock Monitoring",

abstract = "Alpine livestock monitoring is critical for ecological preservation and agricultural efficiency. However, existing solutions struggle with energy constraints, limited network availability, and intermittent connectivity in remote environments. To address this, we propose an on-device federated learning framework tailored for PV-powered IoT sensors to optimize energy-communication tradeoffs. Our approach introduces staleness-aware aggregation and solar-aware training scheduling to address intermittent connectivity and PV variability in remote alpine environments. Deployed on a real-world testbed with collar sensors, the framework achieves 92\% accuracy in time-series location prediction and 89\% F1-score in anomaly detection while using 68\% less energy than centralized baselines.",

author = "Sabtain Ahmad and Thomas Schneidergruber and Ivona Brandic and Johannes Scholz",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.",

year = "2026",

doi = "10.1007/978-3-031-99857-7\_26",

language = "English",

isbn = "9783031998560",

series = "Lecture Notes in Computer Science",

publisher = "Springer Nature Switzerland",

pages = "365--379",

editor = "Nagel, \{Wolfgang E.\} and Diana Goehringer and Diniz, \{Pedro C.\}",

booktitle = "Euro-Par 2025",

}

Ahmad, S, Schneidergruber, T, Brandic, I & Scholz, J 2026, On-Device Federated Learning for Remote Alpine Livestock Monitoring. in WE Nagel, D Goehringer & PC Diniz (eds), Euro-Par 2025: Parallel Processing - 31st European Conference on Parallel and Distributed Processing, Proceedings. Lecture Notes in Computer Science, Springer Nature Switzerland, pp. 365-379. https://doi.org/10.1007/978-3-031-99857-7_26

On-Device Federated Learning for Remote Alpine Livestock Monitoring. / Ahmad, Sabtain; Schneidergruber, Thomas; Brandic, Ivona et al.
Euro-Par 2025: Parallel Processing - 31st European Conference on Parallel and Distributed Processing, Proceedings. ed. / Wolfgang E. Nagel; Diana Goehringer; Pedro C. Diniz. Springer Nature Switzerland, 2026. p. 365-379 (Lecture Notes in Computer Science).

Research output: Chapter in Book/Report/Conference proceeding/Legal commentary › Conference contribution › peer-review

TY - GEN

T1 - On-Device Federated Learning for Remote Alpine Livestock Monitoring

AU - Ahmad, Sabtain

AU - Schneidergruber, Thomas

AU - Brandic, Ivona

AU - Scholz, Johannes

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

PY - 2026

Y1 - 2026

N2 - Alpine livestock monitoring is critical for ecological preservation and agricultural efficiency. However, existing solutions struggle with energy constraints, limited network availability, and intermittent connectivity in remote environments. To address this, we propose an on-device federated learning framework tailored for PV-powered IoT sensors to optimize energy-communication tradeoffs. Our approach introduces staleness-aware aggregation and solar-aware training scheduling to address intermittent connectivity and PV variability in remote alpine environments. Deployed on a real-world testbed with collar sensors, the framework achieves 92% accuracy in time-series location prediction and 89% F1-score in anomaly detection while using 68% less energy than centralized baselines.

AB - Alpine livestock monitoring is critical for ecological preservation and agricultural efficiency. However, existing solutions struggle with energy constraints, limited network availability, and intermittent connectivity in remote environments. To address this, we propose an on-device federated learning framework tailored for PV-powered IoT sensors to optimize energy-communication tradeoffs. Our approach introduces staleness-aware aggregation and solar-aware training scheduling to address intermittent connectivity and PV variability in remote alpine environments. Deployed on a real-world testbed with collar sensors, the framework achieves 92% accuracy in time-series location prediction and 89% F1-score in anomaly detection while using 68% less energy than centralized baselines.

UR - https://doi.org/10.1007/978-3-031-99857-7_26

UR - https://www.scopus.com/pages/publications/105014494889

UR - https://www.mendeley.com/catalogue/96c917ba-312b-3d6e-a13e-94d0d52a3414/

U2 - 10.1007/978-3-031-99857-7_26

DO - 10.1007/978-3-031-99857-7_26

M3 - Conference contribution

SN - 9783031998560

T3 - Lecture Notes in Computer Science

SP - 365

EP - 379

BT - Euro-Par 2025

A2 - Nagel, Wolfgang E.

A2 - Goehringer, Diana

A2 - Diniz, Pedro C.

PB - Springer Nature Switzerland

ER -

Ahmad S, Schneidergruber T, Brandic I, Scholz J. On-Device Federated Learning for Remote Alpine Livestock Monitoring. In Nagel WE, Goehringer D, Diniz PC, editors, Euro-Par 2025: Parallel Processing - 31st European Conference on Parallel and Distributed Processing, Proceedings. Springer Nature Switzerland. 2026. p. 365-379. (Lecture Notes in Computer Science). doi: 10.1007/978-3-031-99857-7_26