학술논문

An Efficient Resource Management Scheme for Smart Grid Using GBO Algorithm
Document Type
Conference
Source
2021 International Conference on Emerging Smart Computing and Informatics (ESCI) Emerging Smart Computing and Informatics (ESCI), 2021 International Conference on. :593-598 Mar, 2021
Subject
Bioengineering
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Fields, Waves and Electromagnetics
Photonics and Electrooptics
Robotics and Control Systems
Signal Processing and Analysis
Cloud computing
Smart meters
Smart grids
Task analysis
Sustainable development
Smart devices
Edge computing
fog computing
cloud computing
smart grid
GBO algorithm
load balancing
Language
Abstract
The smart grid (SG) plays a vital role in the current energy infrastructure and reinforces the reliability, sustainability, efficiency, as well as economics of electricity services. The resourceful use of diverse smart devices in the front-end, including smart meters, is a demanding task and the processing of enormous data received out of these devices is also a major challenge. Cloud computing provides the on-demand services for the computational need but as it has latency issues, fog computing aids cloud computing in providing a favorable method to surmount the SG obstacles. Fog computing in conjunction with cloud computing facilitates energy-saving, cost-saving, flexibility, scalability, and agility. A major issue is the management of resources in SGs. This paper proposed a fog-aided-cloud-based model is proposed for managing the resources in SGs. For enhancing the performance of the proposed fog-aided cloud system, various load balancing techniques are employed. The load amid SG user’s tasks and service providers is balanced by implementing four different meta-heuristic algorithms like particle swarm optimization, ant colony optimization (ACO),artificial bee colony (ABC), and gradient-based optimizer (GBO). Simulation results reveal that GBO which is a newly developed meta-heuristic optimization algorithm outperforms the others.