.png){kind=icon}
.png){kind=icon}
Return
Energy-aware server placement in mobile edge computing using trees social relations optimization algorithm
.png){kind=icon}
PRE
AI
DOI：10.1007/s11227-023-05692-4.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The advent of fifth-generation(5G) telecommunication technology and the rapid growth of smart mobile equipment have led to many processing demands in this area. Many mobile applications developed with this technological growth. In most cases, the services required by mobile cloud users are offered online. The high volume of processes, such as the Internet of Things, online games, electronic education, and e-commerce, which are processing-oriented, consumes a large amount of energy. The limited power of mobile equipment and their battery capacity causes some users' data and applications to be offloaded on network edge servers. Proper server placement has an important impact on their efficiency and energy consumption. The appropriate resource placement can reduce latency and improve energy consumption. Because of the large number of mobile servers, finding the best location of servers is an NP-Hard problem, so researchers have introduced some optimization methods for the problem solution. Parallelization methods can improve the scalability of the resource placement problem and reduce the time complexity of finding the optimal solution. In the proposed method, a novel Energy-aware server placement using the trees social relations algorithm (ESPT), deploying the dynamic voltage and frequency scaling (DVFS) technique, has been introduced for optimal placement of edge servers to extend the network coverage. Our algorithm divides the area into some sub-regions and then, using the modified TSR algorithm, and sharing good solutions, the complexity of the problem is reduced and the global placement of resources is obtained. We evaluated the proposed method under real and synthetic scenarios and in different network conditions and compared it with some related state-of-the-art algorithms. The results of the experiments showed that the proposed method optimizes the energy consumption of mobile servers by up to 13% and also reduces the average network latency by up to 16%.
Keywords:
Edge server placement
Latency
Energy
Trees social relations algorithm
DVFS
Journal
IF:
2.7
Papers:
1.1K
Citations:
1.0W