Deployment optimization of multi-stage investment portfolio service and hybrid intelligent algorithm under edge...

Area of Science:

• Computer Science
• Electrical Engineering
• Telecommunications

Background:

• Traditional edge computing faces challenges in server deployment, leading to increased terminal time delay and energy consumption.
• Mobile Edge Computing (MEC) aims to improve service quality by processing data closer to users.
• Dense network environments in MEC exacerbate issues with task execution efficiency and resource allocation.

Purpose of the Study:

• To enhance server deployment capabilities within Mobile Edge Computing (MEC) environments.
• To reduce terminal time delay and energy consumption during task execution.
• To improve overall user service quality in MEC systems.

Main Methods:

• A multi-stage task resource allocation model integrating task offloading and resource allocation was developed.
• A multi-hybrid intelligent algorithm was proposed for energy consumption optimization in dense MEC networks.
• The algorithm employed heuristic modeling, distributed planning, duality, and upper bound replacement for power allocation.

Main Results:

• The proposed model effectively minimizes maximum task execution energy consumption while optimizing offloading and resource allocation.
• The hybrid intelligent algorithm successfully partitions tasks into sub-problems for efficient offloading and resource management.
• Performance evaluations confirmed the model's effectiveness and superiority over existing algorithms, particularly in user fairness and worst-case energy consumption.

Conclusions:

• The developed multi-stage model and hybrid intelligent algorithm offer a robust solution for server deployment optimization in MEC.
• The findings provide a theoretical foundation and practical insights for MEC server deployment and application design.
• The research successfully addresses key challenges in MEC, improving efficiency, reducing energy use, and enhancing user satisfaction.