In-network Predictive Analytics in Edge Computing

Nikolaou, S., Pezaros, D. and Anagnostopoulos, C. (2019) In-network Predictive Analytics in Edge Computing. In: 11th Annual Wireless Days Conference, Manchester, UK, 24-26 Apr 2019, ISBN 9781728101170 (doi: 10.1109/WD.2019.8734267)

Full text not currently available from Enlighten.


Edge-centric predictive analytics methodologies use real-time model caching to significantly reduce the communication overhead. We investigate an approach of using different regression techniques at the edge as caching models. Our methodology reports on an edge-centric mechanism to automatically decide when to update the parameters of the cached models to a central location (data center). Through experimentation, we showcase the trade off between accuracy and communication overhead and conclude that for all the experimented regression models, a lower percentage of the cached models should be sent to the data center to significantly decrease the communication overhead.

Item Type:Conference Proceedings
Glasgow Author(s) Enlighten ID:Anagnostopoulos, Dr Christos and Nikolaou, Mr Stefanos and Pezaros, Professor Dimitrios
Authors: Nikolaou, S., Pezaros, D., and Anagnostopoulos, C.
College/School:College of Science and Engineering > School of Computing Science

University Staff: Request a correction | Enlighten Editors: Update this record

Project CodeAward NoProject NamePrincipal InvestigatorFunder's NameFunder RefLead Dept
709131Network Measurement as a Service (MaaS)Dimitrios PezarosEngineering and Physical Sciences Research Council (EPSRC)EP/N033957/1COM - COMPUTING SCIENCE
722161FRuIT: The Federated RaspberryPi Micro-Infrastructure TestbedJeremy SingerEngineering and Physical Sciences Research Council (EPSRC)EP/P004024/1COM - COMPUTING SCIENCE
300952HIRP 2017 - Distributed Intelligence for Network ControlDimitrios PezarosHuawei Technologies (CN) (HUAWE-CN)N/AComputing Science