Whale Optimization for Cloud-Edge-Offloading Decision-Making for Smart Grid Services

Area of Science:

• Computer Science
• Electrical Engineering
• Optimization Algorithms

Background:

• Increasing IoT devices in smart grids generate large data volumes, challenging control service latency and secure energy delivery.
• Edge computing offers a solution by offloading computation, but coordinating edge nodes is complex due to vast decision spaces.

Purpose of the Study:

• To develop an optimized method for selecting edge nodes for computational task offloading in smart grids.
• To address challenges in latency, data volume, and secure energy delivery within smart energy grids.

Main Methods:

• Utilized the whale optimization algorithm (WOA) for optimal edge node selection.
• Employed a directed acyclic graph (DAG) to model dependencies and navigate the decision space.
• Developed a fitness function considering round-trip time and edge-task resource correlation for offloading decisions.
• Adapted WOA with modified feedback mechanisms, inertia weight, and convergence factors to prevent suboptimal solutions.

Main Results:

• The proposed solution effectively balances energy and data network constraints.
• Demonstrated faster decision-making for optimization, with response times significantly improved.
• Achieved a low average execution time of approximately 0.03 seconds per iteration.
• Showcased strong performance in diversity, fitness evolution, and execution time on complex infrastructures.

Conclusions:

• The whale optimization algorithm provides an effective approach for edge node selection in smart grids.
• The method enhances optimization speed and resource management while considering network constraints.
• Offers a robust solution for improving the efficiency and reliability of smart energy grids.