Optimal Task Allocation Algorithm Based on Queueing Theory for Future Internet Application in Mobile Edge Computing...

Area of Science:

• Computer Science
• Network Engineering

Background:

• Mobile Edge Computing (MEC) is crucial for 5G and future internet applications, demanding efficient task allocation to minimize latency.
• Existing MEC platforms often involve heterogeneous server environments, including dedicated MEC servers, shared MEC servers, and cloud servers, presenting allocation challenges.

Purpose of the Study:

• To propose a novel task allocation method for mobile edge computing (MEC) platforms to reduce total latency for future internet applications.
• To develop and evaluate a heuristic algorithm for efficient task allocation across dedicated MEC, shared MEC, and cloud servers.

Main Methods:

• Calculated task-response delay considering processing time and transmission delay for each server type (dedicated MEC, shared MEC, cloud).
• Utilized queueing theory to derive transmission delay for shared MEC servers.
• Formulated an optimization problem to minimize total task latency and proposed a heuristic algorithm for approximate optimal solutions.

Main Results:

• The proposed heuristic algorithm demonstrated effectiveness in reducing total latency for task allocation.
• Numerical examples confirmed the algorithm's ability to perform task allocation rapidly and significantly decrease total latency.
• The heuristic algorithm showed comparable or superior performance to existing methods in reducing latency.

Conclusions:

• The developed heuristic algorithm is effective for task allocation in MEC platforms with multiple server types.
• The proposed method offers a practical solution for minimizing latency in demanding 5G and future internet applications.
• Efficient task allocation in heterogeneous MEC environments is key to improving overall system performance.