Energy-efficient Edge Approximation for Connected Vehicular Services
- Resource Type
- Conference
- Authors
- Katare, Dewant; Ding, Aaron Yi
- Source
- 2023 57th Annual Conference on Information Sciences and Systems (CISS) Information Sciences and Systems (CISS), 2023 57th Annual Conference on. :1-6 Mar, 2023
- Subject
- Communication, Networking and Broadcast Technologies
Computing and Processing
Photonics and Electrooptics
Robotics and Control Systems
Signal Processing and Analysis
Energy consumption
Three-dimensional displays
Pipelines
Ecosystems
Focusing
Data processing
Energy efficiency
3D maps
Approximation
Data Compression
Energy Efficiency
Edge AI
HD map
Model compression
- Language
Connected vehicular services depend heavily on communication as they frequently transmit data and AI models/weights within the vehicular ecosystem. Energy efficiency in vehicles is crucial to keep up with the fast-growing demand for vehicular data processing and communication. To tackle this rising challenge, we explore approximation and edge AI techniques for achieving energy efficiency for vehicular services. Focusing on data-intensive vehicular services, we present an experimental case study on the high-definition (HD) map using the model partition approach. Our study compares the AI model energy consumption using multiple approximation ratios over embedded edge devices. Based on experimental insights, we further discuss an envisioned approximate Edge AI pipeline for developing and deploying energy-efficient vehicular services.