Software-defined networking (SDN) and network function virtualization (NFV) processed in multi-access edge computing (MEC) cloud systems have been proposed as critical paradigms for achieving the low latency requirements of the tactile Internet. While virtual network functions (VNFs) allow greater flexibility compared to hardware-based solutions, the VNF abstraction also introduces additional packet processing delays. In this paper, we investigate the practical feasibility of NFV with respect to the tactile Internet latency requirements. We develop, implement, and evaluate Chain-based Low latency VNF ImplemeNtation (CALVIN), a low-latency management framework for distributed Service Function Chains (SFCs). CALVIN classifies VNFs into elementary, basic, and advanced VNFs; moreover, CALVIN implements elementary and basic VNFs in the kernel space, while the advanced VNFs are implemented in the user space. Throughout, CALVIN employs a distributed mapping with one VNF per Virtual Machine (VM) in a MEC system. Furthermore, CALVIN avoids the metadata structure processing and batch processing of packets in the conventional Linux networking stack so as to achieve short per-packet latencies. Our rigorous measurements on off-the-shelf conventional networking and computing hardware demonstrate that CALVIN achieves round-trip times from a MEC ingress point via two elementary forwarding VNFs (one in kernel space and one in user space) and a MEC server to a MEC egress point on the order of 0.32 ms. Our measurements also indicate that MEC network coding and encryption are feasible for small 256 byte packets with an MEC latency budget of 0.35 ms; whereas, large 1400 byte packets can complete the network coding, but not the encryption within the 0.35 ms.

Emerging microservices demand flexible low-latency processing of network functions in virtualized environments, e.g., as containerized network functions (CNFs). While ensuring highly responsive low-latency CNF processing, the computing environments should conserve energy to reduce costs. In this systems integration study, we develop and evaluate the novel XDP-Monitoring Energy-Adaptive Network Functions (X-MAN) framework for managing the CPU operational states (P-states) so as to reduce the power consumption while prioritizing low-latency service. Architecturally, X-MAN consists of lightweight traffic monitors that are attached to the virtual network interfaces in the kernel space for per-CNF traffic monitoring and a power manager in user space with a global view of the CNFs on a CPU core. Algorithmically, X-MAN monitors the CPU core utilization via hybrid simple and weighted moving average prediction fed by the traffic monitors and a power management based on step-based CPU core frequency (P-state) adjustments. We evaluate X-MAN through extensive measurements in a real physical testbed operating at up to 10 Gbps. We find that X-MAN incurs significantly shorter and more consistent monitoring latencies for the CPU utilization than a state-of-the-art CPU hardware counter approach. Also, X-MAN achieves more responsive CPU core frequency adjustments and more pronounced reductions of the CPU power consumption than a state-of-the-art code instrumentation approach. We make the X-MAN source code publicly available.

With increasing numbers of computer vision and object detection application scenarios, those requiring ultra-low service latency times have become increasingly prominent; e.g., those for autonomous and connected vehicles or smart city applications. The incorporation of machine learning through the applications of trained models in these scenarios can pose a computational challenge. The softwarization of networks provides opportunities to incorporate computing into the network, increasing flexibility by distributing workloads through offloading from client and edge nodes over in-network nodes to servers. In this article, we present an example for splitting the inference component of the YOLOv2 trained machine learning model between client, network, and service side processing to reduce the overall service latency. Assuming a client has 20% of the server computational resources, we observe a more than 12-fold reduction of service latency when incorporating our service split compared to on-client processing and and an increase in speed of more than 25% compared to performing everything on the server. Our approach is not only applicable to object detection, but can also be applied in a broad variety of machine learning-based applications and services.

Understanding and quantifying the factors that lead to cheating in society is problematic, due to the inherent desire to hide socially unacceptable actions. While significant progress has been made in the understanding of unethical behavior via in-lab experiments, little was measured at scale, in the wild. By analyzing cheating in online games, this paper verifies at scale and in the wild a number of previous observations drew from controlled, in-lab experiments. We verify empirically that cheating behavior is contagious, and identify some of the factors that encourage cheating and some that limit it.