Serving at the Edge: An Edge Computing Service Architecture Based on ICN

Abstract

Different from cloud computing, edge computing moves computing away from the centralized data center and closer to the end-user. Therefore, with the large-scale deployment of edge services, it becomes a new challenge of how to dynamically select the appropriate edge server for computing requesters based on the edge server and network status. In the TCP/IP architecture, edge computing applications rely on centralized proxy servers to select an appropriate edge server, which leads to additional network overhead and increases service response latency. Due to its powerful forwarding plane, Information-Centric Networking (ICN) has the potential to provide more efficient networking support for edge computing than TCP/IP. However, traditional ICN only addresses named data and cannot well support the handle of dynamic content. In this article, we propose an edge computing service architecture based on ICN, which contains the edge computing service session model, service request forwarding strategies, and service dynamic deployment mechanism. The proposed service session model can not only keep the overhead low but also push the results to the computing requester immediately once the computing is completed. However, the service request forwarding strategies can forward computing requests to an appropriate edge server in a distributed manner. Compared with the TCP/IP-based proxy solution, our forwarding strategy can avoid unnecessary network transmissions, thereby reducing the service completion time. Moreover, the service dynamic deployment mechanism decides whether to deploy an edge service on an edge server based on service popularity, so that edge services can be dynamically deployed to hotspot, further reducing the service completion time.

[Retracted] Construction of Smart Higher Education Teaching Resources Using Data Analysis Technology in Unbalanced Data Environment

“…Lee and Cho advocate the use of big data applications in personalised teaching, tailored learning, and personalised engagement because they believe that big data can address the monotonous problem of educational techniques and advance the development of personalised education [ 18 ]. Fan and Yang provided a detailed process of data mining service modeling in a cloud environment [ 19 ] and presented a data mining service architecture based on cloud computing. Mao et al use the Apriori algorithm of association rules to analyze the relationship between admission results and candidates' categories and regional grades, allowing education managers to quickly understand the development of education levels in the region and providing more reasonable decisions for the overall arrangement of limited educational resources support [ 20 ].…”

MIA-NDN: Microservice-Centric Interest Aggregation in Named Data Networking

“…In this section, we describe the experimental environment, implementation, and evaluation of the proposed MIA-NDN scheme against the most recent existing solution [ 21 ].…”

“…To evaluate the effectiveness of MIA-NDN, we performed extensive simulations in NDNSim (an ns3-based simulator on a computer equipped with Core i5, 16 GB of RAM) and compared the results with the state-of-the-art scheme named Serving at the Edge (SATE) [ 21 ]. In our simulation environment, we consider 10 nodes, with 2 edges, 2 consumers, 6 NDN routers, and a cloud equipped with computation, communication, and storage units.…”

“…Researchers have focused on different state-of-the-art schemes [ 19 , 20 , 21 ] in the literature, mainly targeting effective in-network service computations. The scheme presented in [ 19 ] sends a computing request to the producer and the producer estimates the request execution time, generates the acknowledgment packet, and sends it back to the consumer to adjust the PIT lifetime and maintain the entry of intermediate nodes.…”

“…A similar scheme proposed in [ 20 ] first inquires about the potential function executor by forwarding computing interests and generating a separate interest packet to carry the remote method invocation parameters toward the potential forwarder, maintaining a 5 s static PIT lifetime for computation request entries. Another service execution scheme named "serving at the edge” presented in [ 21 ] forwards the interest toward the compute node. The compute node informs the consumer about the execution via an acknowledgment packet and pushes the results back toward the consumer after generating the results.…”