Wireless networks are pivotal to modern communication, yet traditional address-centric protocols often fail to leverage the inherent advantages of wireless transmission potentials in dynamic edge environments. While Information-centric Networking (ICN) offers promising data-centric alternatives, the integration with wireless systems in resource-constrained edge settings faces critical challenges including channel instability, unreliable transmission, and fluctuating link quality. This paper introduces RENCA, a framework designed to enable seamless NDN-based wireless communication tailored for edge environments. RENCA addresses these challenges through three key innovations. First, it introduces a distributed collision avoidance strategy that leverages wireless broadcast properties to select high-quality communication pairs in real time, minimizing localized interference in wireless networks. Second, it incorporates a reliable transmission mechanism using Selective Negative Acknowledgement (SNAK) to ensure data integrity while aligning with content-centric principles in dynamic edge topologies. Third, it presents a dynamic Modulation Coding Scheme (MCS) adaptation that improves communication goodput in response to real-time channel fluctuations. We implement the entire RENCA protocol stack on real wireless hardware and drivers, and conduct extensive experiments over real wireless scenarios. The system achieves a 92.96% overall goodput improvement in multi-device edge environments compared to traditional protocols, demonstrating the usefulness of robust, high-performance communication for edge applications.

The rapid evolution of wireless edge computing faces fundamental limitations from connection-oriented protocols, particularly in dynamic scenarios with distributed edge environments. In this paper, we present SWICE, a novel transmission system with modified frame injection techniques that eliminates connection establishment overhead while ensuring reliable data delivery in wireless distributed edge environments. Our system introduces a connection-free measurement strategy that uses minimal packets to assess communication status while keeping device identities private. We formulate an edge node selection problem for efficiency and develop a heuristic algorithm for optimal data delivery. Additionally, we implement a reliability mechanism that combines adaptive retransmission to enhance communication stability. We conduct real-world experiments with commercially available Wi-Fi devices and modified wireless radios. The results show that SWICE achieves up to a 36.88 % increase in goodput compared to conventional transmission methods, demonstrating its effectiveness through real-world experiments.

HTTP/3 is designed to enhance performance and security by utilizing QUIC as its underlying transport protocol. Integrating HTTP/3 and its features can expand the application scope of ICN. Through an analysis of critical elements of HTTP/3, we implement it on NDN forwarding daemons and run applications in browsers to assess its capabilities and potential benefits in ICN environments. Our system demonstration illustrates compatibility with mainstream browsers while supporting ICN-based transmissions.

Information-centric Networking in edge computing environments exhibits the potential to significantly enhance the efficiency, reliability, and security of data transmission, making it a promising technology for future network deployments. However, the differences from traditional networks require applications to actively redevelop and redeploy onto edge devices, incurring additional costs for the proliferation of ICN applications. In this paper, we propose a system to adapt QUIC protocol over ICN networks in multi-access edge networks. The system aims to expand the application repertoire for ICN by providing a smooth transition of applications using QUIC to run on ICN networks. We design an ICN-QUIC conversion layer to manage the transmission of data from QUIC-based applications. We implement and evaluate the designed system. The experiment results show that, compared to existing networks, our system can enhance the transmission efficiency, i.e., up to 20 times better goodput in multicast situations, and achieves comparable results in unicast scenarios. We test the scalability of our system in real edge and wireless environments. We also deploy the real applications over the proposed system to demonstrate its compatibility in ICN and MEC environments.

Serverless Computing and Function-as-a-Service (FaaS) offer convenient and transparent services to developers and users. The deployment and resource allocation of services are managed by the cloud service providers. Meanwhile, the development of smart mobile devices and network technology enables the collection and transmission of a huge amount of data, which shifts tasks to the network edge for mobile users. In this paper, we propose a deviceless edge computing system targeting the mobility of end users using the data migration of virtual functions. We focus on the adjustment of migration among virtual functions to provide uninterrupted services to mobile users. We introduce the deviceless edge computing model and propose a seamless data migration scheme of virtual functions with limited involvement of function developers. We formulate the migration decision problem into integer linear programming and use receding horizon control (RHC) for online solutions. We implement the migration system to support delay-sensitive scenarios over real edge devices and develop a streaming game as the virtual function to test the performance. Extensive experiments in real scenarios exhibit the system has the ability to support high-mobility and delay-sensitive application scenarios. Extensive simulation results show the applicability of the proposed system over large-scale networks.