Energy Efficient Edge Computing Enabled by Satisfaction Games and Approximate Computing
- 26 October 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Green Communications and Networking
- Vol. 6 (1) , 281-294
Abstract
In this paper, we introduce an energy efficient edge computing solution to collaboratively utilize Multi-access Edge Computing (MEC) and Fully Autonomous Aerial Systems (FAAS) to support the computing demands of the Internet of Things (IoT) nodes residing in Areas of Interest (AoIs) and executing machine learning tasks. The Satisfaction Games are adopted to determine whether the nodes’ optimal partial task should be offloaded to the MEC server or to a hovering FAAS above the AoI. The decision is taken by considering IoT nodes’ latency, energy consumption, and acceptable level of Deep Neural Network (DNN) inference accuracy drop constraints. We exploit the error resilience of DNNs and we enhance the FAAS with a heterogeneous approximate DNN accelerator that supports different computational precision and throughput, thus allowing to intelligently adapt to different computing demands. A reinforcement learning-based technique is introduced to enable the FAAS to autonomously optimize its trajectory, aiming at increasing the IoT nodes’ satisfaction of their computing demands, while accounting for its flying and data processing energy cost. Our experimental results show the benefits of FAAS, MEC, and approximate computing in terms of increasing the number of satisfied users by 40% under a maximum accuracy drop of only 1%.Keywords
Funding Information
- German Research Foundation (DFG) through the Project “ACCROSS: Approximate Computing Across the System Stack.”
- NSF (CRII-1849739)
This publication has 30 references indexed in Scilit:
- Energy-efficient neural networks using approximate computation reuse2018
- UNPU: A 50.6TOPS/W unified deep neural network accelerator with 1b-to-16b fully-variable weight bit-precision2018
- UAV-Assisted Dynamic Coverage in a Heterogeneous Cellular SystemIEEE Network, 2017
- In-Datacenter Performance Analysis of a Tensor Processing Unit2017
- Mobile Edge Computing via a UAV-Mounted Cloudlet: Optimization of Bit Allocation and Path PlanningIEEE Transactions on Vehicular Technology, 2017
- 14.2 DNPU: An 8.1TOPS/W reconfigurable CNN-RNN processor for general-purpose deep neural networks2017
- Design of power-efficient approximate multipliers for approximate artificial neural networks2016
- Quality-Of-Service Provisioning in Decentralized Networks: A Satisfaction Equilibrium ApproachIEEE Journal of Selected Topics in Signal Processing, 2011
- ImageNet: A large-scale hierarchical image database2009
- A tutorial on decomposition methods for network utility maximizationIEEE Journal on Selected Areas in Communications, 2006