Flexible architecture for deployment of edge computing applications

Recently, a great development has occurred in the communication networks, in which the trend of development is towards automation and flexible network structure. In addition, the stages of telecommunication development are conventionally divided from manual switching to flexible virtualized architecture, to which telecommunications operators have resorted. Furthermore, in the context of the 3rd generation partnership project (3GPP) standards framework, the network function virtualization (NFV) with might and main has been evaluated by telecom operators and shows that the efficiency of the topology can be significantly improved. However, it is difficult to organize ultra-reliable low-latency communication (URLLC) and massive machine type communications (mMTC) services within 5G, due to the topology centralization. Moreover, network monitoring, in particular of carrier-class equipment, reveals that there is no ideal static network topology in which the network and its elements have been uniformly loaded over a long service time. Therefore, in this study, a dynamic network topology and service placement is proposed to analyze and predict services, in which Genetic Algorithm (GA) is utilized. In addition, an efficient forecasting and live migration methods of service as an application to edge computing systems are introduced, where this approach can be used in the systems with an intelligent allocation of operator equipment resources for providing flexibility and high-quality topological organization. Finally, simulation results proved that the network equipment efficiency can significantly be increased by more than 30%. © 2021 Elsevier B.V.