Network Function Virtualization (NFV) is a system that provides application services by connecting virtual network functions (VNFs), and is expected to accommodate new service requests through the development of new VNF and connection with existing ones. Because VNFs are implemented by software, their design and placement are important problems for the NFV system, which reduce the current and future system costs. In this paper, we investigate the design principles and the placement policies that reduce the cost of designing and developing VNFs for accommodating new service requests. As for the design policy, we introduce a Core/Periphery-Based Design (CPBD) that utilizes the core/periphery concept for developing VNFs. In CPBD, "core" VNFs are developed in advance and repeatedly used to accommodate future service requests. While "core" VNFs are common to current and future service requests, "periphery" VNFs are developed and customized for each service request. Next, we investigate the placement policies of VNFs for CPBD to fully utilize the nature of their core/periphery structure. In addition, we examine the Center-Located Core/Periphery placement (CLCP) policy and the Geographically-Distributed Core/Periphery placement (GDCP) policy, and evaluate the long-term cost of the NFV system under resource restrictions to run VNFs. Our results show that CPBD reduces the long-term cost of design and development of VNFs by 23% compared to the design with no core VNFs. Moreover, in the case of no resource restrictions, both CLCP and GDCP reduce the long-term costs of placing and connecting VNFs by 15% compared to the existing VNF placement algorithm. With resource constraints, GDCP reduces the long-term costs over CLCP by 11%.
Many new network-oriented services have been developed in recent years, and Multi-access Edge Computing (MEC) has been standardized to improve the responsiveness of services. When deploying services in a MEC environment, it is necessary to consider a service structure that can flexibly switch service behaviors to meet various user requests and that can change service behaviors according to the real-world environment at a low implementation cost. In this paper, we introduce a core/periphery structure for service components, which is known as a model for flexible behavior in biological systems, and design and implement a network-oriented mixed reality service based on this structure. We investigate what kinds of functions should be developed to accommodate user requests in conjunction with various types of devices and real-world environments in which users and devices are located. To utilize the flexibility of a core/periphery structure, we regard core functions as those whose behaviors remain unchanged even when there are changes in user requests or the environment. In contrast, peripheral functions are those whose behaviors can change under such circumstances. Experiments reveal that implementation costs are reduced while retaining increases in service response time to less than 31 ms. These results show that taking advantage of a core/periphery structure allows appropriate division of service functions and placement of functions in a MEC environment, with only small penalties on latency and at a low implementation cost.
In the recent years, many new network-oriented services have emerged, and such services will need to be virtualized in the multi-access edge computing (MEC) environment, which is currently being standardized along with fifth generation (5G). The service design should be adaptable to user requirements and environmental changes for accommodating a large number of services at low cost. In addition, it is required not only to assume environmental changes when initially designing the service functions network, but also to enable the network to continue to change its structure to adapt to new environmental changes in the future. We have been investigated a core/periphery structure that allows service to effectively adapt to each user request and environmental variation. The advantage of the core/periphery structure is that it helps reduce the costs for maintaining or changing services by distinguishing the service functions into core and periphery functions. In this paper, we propose a method to evolve service functions network based on a core/periphery structure. Adapting to environmental changes requires the addition of interfaces between service functions or the development of new service functions. Our method evolves the structure of the service function network at low cost by keeping the core and peripheral functions at the appropriate scale. Our simulation results reveal that the structure of the service function networks can continue to evolve for a low cost and can maintain a high service accommodation ratio.
In recent years, many new network-oriented services have emerged, and such services will need to be virtualized in the multi-access edge computing environment, which is currently being standardized along with fifth-generation network technology. The environment surrounding the service functions network changes over time, such as breaking changes of APIs, and these changes impact the services. The service design should be adaptable to user requirements and environmental changes for accommodating a large number of services at low cost. In addition, it is required not only to assume environmental changes when initially designing the service functions network, but also to enable the network to continue to change its structure to adapt to new environmental changes in the future. In this paper, we propose a method to evolve the entire network of service functions based on a core/periphery structure. The advantage of the core/periphery structure is that it helps reduce the costs for maintaining or changing services by dividing the service functions into core and periphery functions. We propose a method to evolve a service functions network based on this core/periphery structure. Our method evolves the structure of the service functions network at low cost by keeping the core and peripheral functions at the appropriate scale. In addition, our proposed method accommodates almost 100% of randomly generated service chains, and holds their length to less than twice the minimum chain length. Our simulation results reveal that the structure of the service functions networks can continue to evolve at a low cost and maintain a high service accommodation ratio.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with đź’™ for researchers
Part of the Research Solutions Family.