Research on MEC computing offload strategy for joint optimization of delay and energy consumption

Area of Science:

• Computer Science
• Artificial Intelligence
• Network Engineering

Background:

• Computational offloading is key in mobile edge computing (MEC).
• Offloading decisions heavily influence system latency and energy consumption.
• Existing strategies require optimization for efficient edge-end architectures.

Purpose of the Study:

• To propose an optimized computational offloading scheme for edge-end MEC architectures.
• To introduce an enhanced sine-cosine optimization algorithm (SCAGA) for improved offloading decisions.
• To evaluate the performance of the SCAGA-based scheme in reducing latency and enhancing offloading utility.

Main Methods:

• Developed computational resource and cost models for edge computing.
• Introduced SCAGA, integrating Levy flight, roulette wheel selection, and gene mutation.
• Conducted simulation experiments to assess the SCAGA offloading scheme.

Main Results:

• The SCAGA-based offloading scheme significantly reduced system latency.
• Optimized offloading utility was achieved using the proposed SCAGA.
• Comparative analysis showed SCAGA outperformed alternative schemes in latency, energy consumption, and utility.

Conclusions:

• The SCAGA scheme offers an effective solution for computational offloading in edge-end MEC.
• SCAGA demonstrates superior performance in balancing latency, energy, and utility.
• This research contributes to efficient resource management in mobile edge computing environments.