With the rapid development of programmable data plane (PDP), both segment routing (SR) and in-band network telemetry (INT) have attracted intensive interests. Hence, we have previously proposed the technique of SR-INT, which explores the benefits of SR and INT simultaneously and gets rid of the hassle of the accumulated overheads of them. In this work, we further expand the advantage of SR-INT by studying how to plan the SR-INT schemes of flows at the network level to balance the tradeoff between bandwidth usage and coverage of network monitoring, namely, the problem of “SR-INT orchestration”. A mixed integer linear programming model (MILP) is first formulated for the problem, and we prove its NP-hardness. Then, to reduce the time complexity of problem-solving, we propose a novel greedy algorithm based on path ranking and a column generation (CG) based approximation algorithm. Extensive simulations verify the performance of our proposed algorithms.

As a promising network monitoring technique, in-band network telemetry (INT) helps to visualize networks in a fine-grained and real-time manner. Meanwhile, to address the overheads of INT, people have proposed a few selective INT (Sel-INT) approaches that only select a portion of packets in each flow to insert INT fields and distribute different types of INT fields over the selected packets. In this paper, we study how to use Sel-INT wisely in a network such that the tradeoff between monitoring accuracy/coverage and INT overheads can be balanced well. Specifically, we try to orchestrate the Sel-INT schemes of flows in both network- and flow-levels. For the network-level optimization, we model it as an INT planning problem in which the Sel-INT schemes of flows should be determined to maximize the information gain of INT as well as minimize the bandwidth overheads of INT. We formulate an integer linear programming (ILP) model to tackle the problem, prove its$\mathcal {N} \mathcal {P}$-hardness, and leverage Lagrangian relaxation to design a polynomial-time approximation algorithm for it. The flow-level optimization considers a dynamic network environment, and we propose to combine deep learning (DL) based traffic prediction with Sel-INT, such that the Sel-INT scheme of each individual flow can be updated timely and adaptively. We implement the proposal in a small but real network testbed and experimentally demonstrate self-adaptive orchestration of Sel-INT with it.

With momentum gained from programmable data plane (PDP), in-band network telemetry (INT) has been widely considered as a promising technique for realtime network monitoring. In this work, we leverage network coding (NC) to design CodedINT, for improving the visibility of INT in lossy networks. Specifically, we propose to encode the telemetry data in multiple packets with NC and distribute the encoded data over a group of packets. Then, among the group of packets, if we can receive enough ones that satisfy the decoding condition of NC, the whole original telemetry data can be recovered. We first explain the design of CodedINT to elaborate on its operation principle, packet format, and system implementation. Then, we implement and experimentally evaluate CodedINT in a real network testbed. Our experiments demonstrate that in a lossy network with packet loss rate at 80%, CodedINT ensures that 89.48% of the telemetry data carried by INT packets can be recovered successfully.

The advances on hybrid optical/electrical DCNs (HOE-DCNs) make it easier to support network function virtualization (NFV) with various quality-of-service (QoS) demands. However, the existing approaches for NFV orchestration rely heavily on the control plane, which might lead to scalability and performance issues. In this work, we propose to offload certain network orchestration tasks from the control plane to top-of-rack (ToR) switches, by leveraging the flexibility of programmable data plane (PDP). Specifically, we architect an HOE-DCN whose ToR switches are PDP switches, design the network orchestration system for it, and program the ToR switches, such that they can make quick decisions locally to assist the control plane to provision the service chains of virtual network functions (vNF-SCs) agilely. We prototype our proposal in a small-scale HOE-DCN testbed, and the experimental results show that without much involvement of the control plane, the ToR switches can make local decisions and readjust the provisioning schemes of vNF-SCs adaptively to satisfy their QoS demands.

In this work, we try to combine software-defined networking (SDN), in-band network telemetry (INT), and data analytics to realize a novel closed-loop network automation system. To architect the data plane, we jointly consider P4-based and protocol-oblivious forwarding (POF) based programmable data plane switches (PDP-SWs) to build a generic programmable data plane (G-PDP), such that the two types of PDP-SWs can benefit each other mutually to overcome their own drawbacks. In the control plane, we expand ONOS to ensure that it can effectively manage the PDP-SWs in the G-PDP. We also design and implement data analyzers (DAs) in its data analytics subsystem, and deploy them distributedly in the G-PDP to alleviate the burden of data processing in the control plane. Our proposal is demonstrated experimentally with a network system prototype that consists of six PDP-SWs, and the results confirm that it can realize closed-loop network automation effectively and balance the tradeoff between flexibility and performance properly.

The rapid development of software-defined networking (SDN) has promoted the idea of programmable data plane (PDP), which opens up unprecedented opportunities for realizing powerful and timely network monitoring. This work explores the advantages of PDP to merge two famous techniques (i.e., the segment routing (SR) and in-band network telemetry (INT)) seamlessly for highly-efficient and adaptive network monitoring. Specifically, by leveraging the protocol-oblivious forwarding (POF), we propose SR-INT, which time-multiplexes the header fields in each packet for INT and SR, and keeps packet length constant end-to-end even though both INT and SR are used. Hence, our proposal can enjoy the benefits of INT and SR, while avoiding the accumulated overheads due to simultaneous usage. We design the packet format of SR-INT, and lay out its packet processing procedure to guarantee that the configuration of SR-INT can be adjusted dynamically to adapt to the requirements of network monitoring. We implement and experimentally demonstrate SR-INT in a POF-based SDN environment. Our results show that SR-INT not only reduces the bandwidth overheads of using SR and INT simultaneously but also simplifies the operations in software-based POF switches.

It is known that by leveraging programmable data plane, in-band network telemetry (INT) can be realized to provide a powerful and promising method to collect realtime network statistics for monitoring and troubleshooting. However, existing INT implementations still exhibit a few drawbacks such as lack of runtime-programmability and relatively high overheads due to per-packet operation. In this work, we propose and design a runtime-programmable selective INT system, namely, Sel-INT, to resolve these issues. Specifically, we first design a runtime-programmable selective INT scheme based on protocol oblivious forwarding (POF), and then prototype our design by extending the famous OpenvSwitch (OVS) platform to obtain a software switch that supports Sel-INT and implementing a Data Analyzer to parse, extract and analyze the INT data. Our implementation of Sel-INT is verified and evaluated in a real network testbed that consists of a few stand-alone software switches. The experimental results demonstrate that Sel-INT can not only adjust the sampling rate of INT in runtime but also program the corresponding data types dynamically, and they also confirm that our proposal can ensure proper accuracy and timeliness for network monitoring while greatly reducing the overheads of INT.

In the Internet, to enable emerging network services such as e-Health to be delivered to numerous people anytime and anywhere, mobility management plays an important role. In this work, we leverage the protocol-oblivious forwarding (POF) to design a novel network system that can realize highly-efficient mobility management and overcome the drawbacks of existing approaches. Moreover, we explore the forwarding plane programmability provided by POF to realize dynamic virtual network function (vNF) deployment for traffic adaption. We implement our system and conduct experiments to verify that it functions well for NFV-assisted mobility management and achieves reduced handover latency and enhanced QoE.