ESCOVE: Energy-SLA-Aware Edge-Cloud Computation Offloading in Vehicular Networks

Area of Science:

• Intelligent Transportation Systems
• Edge and Cloud Computing
• Vehicular Networks

Background:

• Vehicular networks support intelligent transportation applications, requiring computation offloading to edge and cloud servers due to vehicle limitations.
• Optimizing energy consumption in edge-cloud platforms is critical, but current research often neglects Quality of Service (QoS).

Purpose of the Study:

• To propose a novel offloading algorithm, ESCOVE, that optimizes energy consumption for edge-cloud platforms in vehicular networks.
• To ensure that the proposed algorithm maintains Service Level Agreements (SLAs) regarding latency, processing, and execution times.

Main Methods:

• Development of the ESCOVE offloading algorithm.
• Integration of energy optimization with SLA considerations for vehicular applications.
• Comparative experimental analysis against existing state-of-the-art approaches.

Main Results:

• ESCOVE demonstrates significant energy savings in the edge-cloud computing platform.
• The algorithm successfully preserves Service Level Agreements (SLAs) for vehicular applications.
• Experimental results validate ESCOVE's effectiveness compared to current methods.

Conclusions:

• ESCOVE presents a promising solution for energy-efficient edge-cloud computing in intelligent transportation.
• The algorithm balances energy optimization with the critical QoS requirements of vehicular services.
• This work addresses a gap in research by considering both energy and SLA in vehicular edge-cloud offloading.