Heterogeneous Resource Management for Services based on Artificial Intelligence

Thumbnail Image
Journal Title
Journal ISSN
Volume Title
School of Science | Doctoral thesis (article-based) | Defence date: 2023-07-31
Degree programme
103 + app. 109
Aalto University publication series DOCTORAL THESES, 97/2023
Machine-to-machine communication (M2M) is becoming the most significant share of wireless traffic, largely due to emerging applications in the Internet of Things (IoT) including those for smart cities and intelligent transportation systems. A large number of such applications leverage artificial intelligence (AI) through machine learning (ML) and have heterogeneous resource requirements. To this end, several novel computing and communication paradigms have been proposed, including cloud, fog, edge, and network slicing. This dissertation addresses heterogeneous resource management for AI-based services with a focus on distributed processing and IoT scenarios. Specifically, we leverage the fog and edge computing paradigms for efficient management of resources including processing, communication, and AI knowledge. First, we consider how to achieve fast and scalable deep neural network (DNN) inference involving IoT devices. Accordingly, we propose distributed techniques that collaboratively partition and offload computation under dynamic network conditions to minimize DNN inference time. Second, we develop a tool to improve the DNN inference time through fast sparse matrix-vector multiplication (SpMV), which is a major computing operation for pruned DNNs. The related data structures and algorithms are selected through a rigorous analysis of sparsity and prediction of the related performance. Next, we focus on efficient network resource utilization while providing a target service quality. In detail, we leverage slicing and Fog-RANs to improve resource utilization for generic services in 5G networks with multiple service providers. To this end, we propose a hierarchical resource scheduling mechanism named 2L-MRA to jointly allocate multiple Fog-RAN resources to network slices in two stages. Finally, we target improving the accuracy of the DNNs by developing an economic market that incentivizes different service providers to trade and combine their existing knowledge for higher model accuracy. Specifically, we devise a model based on Fisher's market for optimal knowledge sharing through transfer learning and a weight fusion technique to merge the acquired knowledge.
Supervising professor
Di Francesco, Mario, Prof., Aalto University, Department of Computer Science, Finland
distributed inference, DNN offloading, edge computing, heterogeneous resources, network economics
Other note
  • [Publication 1]: Yuzhe Xu, Thaha Mohammed, Mario Di Francesco, and Carlo Fischione. Distributed Assignment with Load Balancing for DNN Inference at the Edge. IEEE Internet of Things Journal, vol. 10, no. 2, pp. 1053-1065, September 2022.
    Full text in Acris/Aaltodoc: http://urn.fi/URN:NBN:fi:aalto-202209145574
    DOI: 10.1109/JIOT.2022.3205410 View at publisher
  • [Publication 2]: Thaha Mohammed, Carlee Joe-Wong, Rohit Babbar, and Mario Di Francesco. Distributed Inference Acceleration with Adaptive DNN Partitioning and Offloading. In Proceedings of the 39th IEEE InternationalConference on Computer Communications (IEEE INFOCOM 2020), Toronto, pp.854–863, 5523, July 2020.
    Full text in Acris/Aaltodoc: http://urn.fi/URN:NBN:fi:aalto-202010025736
    DOI: 10.1109/INFOCOM41043.2020.9155237 View at publisher
  • [Publication 3]: Thaha Mohammed, Aiiad Albeshri, Iyad Katib, and Rashid Mehmood. DIESEL: A novel deep learning-based tool for SpMV computations and solving sparse linear equation systems. The Journal of Supercomputing, vol. 77, no. 6, pp.6313–6355, October 2020.
    DOI: 10.1007/s11227-020-03489-3 View at publisher
  • [Publication 4]: Thaha Mohammed, Behrouz Jedari, and Mario Di Francesco. Efficient and Fair Multi-Resource Allocation in Dynamic Fog Radio Access Network Slicing. IEEE Internet of Things Journal, vol. 9, no. 24, pp. 24600–24614, July 2022.
    Full text in Acris/Aaltodoc: http://urn.fi/URN:NBN:fi:aalto-202208104526
    DOI: 10.1109/JIOT.2022.3192291 View at publisher
  • [Publication 5]: Thaha Mohammed, Si-Ahmed Naas, Stephan Sigg, and Mario Di Francesco. Knowledge Sharing in AI Services: A Market-based Approach. IEEE Internet of Things Journal, vol. 10, no. 2, pp. 1320-1331, September 2022.
    Full text in Acris/Aaltodoc: http://urn.fi/URN:NBN:fi:aalto-202209215643
    DOI: 10.1109/JIOT.2022.3206585 View at publisher