The objective of congestion control is to maximize network bandwidth utilization and minimize the average flow completion time in data center networks. Key performance indicators required to achieve this objective are high throughput and low packet latency. Existing approaches have proposed various methods to control packet delivery based on various network events or parameters such as packet loss, bottleneck bandwidth, RTT, and queue length. However, these methods often result in suboptimal packet transmission states that compromise throughput or latency. We provide a method to overcome this drawback. To this end, we introduce a congestion control method called PRTT (Predicted RTT) that leverages predicted RTT for congestion control. By using accurately predicted RTT values, PRTT dynamically adjusts the packet delivery rate to control the number of in-flight packets. This enables the transmission to approach states where the buffer holds only a few packets while fully utilizing the link bandwidth. Experimental results show that PRTT achieves higher throughput, lower latency, and shorter flow completion times than other state-of-the-art methods, particularly under bursty traffic. These results demonstrate that PRTT offers a promising solution for congestion control.

Accurate per-flow measurement is essential for effective network management in programmable networks. However, achieving this accuracy remains challenging due to limited switch resources and the massive scale of network flows. Existing sketch-based methods often encounter significant measurement errors, particularly when dealing with the large number of extremely small flows, known as "ant flows". To address this issue, this paper introduces Mix Sketch, a novel measurement framework designed for differentiated and precise per-flow measurement. Mix Sketch uniquely categorizes traffic into elephant, mouse, and ant flows, and employs a tailored three-level structure to measure each flow category appropriately. This approach significantly enhances measurement accuracy, especially for ant flows. Furthermore, we propose Co-Mix Sketch, a lightweight collaborative measurement scheme that leverages network topology to distribute Mix Sketch components across different node tiers, thereby optimizing resource utilization and improving accuracy without requiring complex coordination. Evaluations conducted on real-world traffic traces demonstrate that Mix Sketch substantially outperforms baseline single-node methods, while Co-Mix Sketch achieves notable accuracy improvements with minimal overhead compared to existing collaborative approaches.

The paper addresses the challenge of scheduling multiple output priority queues of a switch in a real-world setting characterized by bursty traffic and diverse traffic priorities. Existing queue scheduling methods primarily employ two types of strategies: priority-based scheduling and weight-based scheduling. However, there is a lack of scheduling methods that can simultaneously handle bursty traffic in a timely manner and maintain priority-based scheduling. This paper addresses this issue by formulating the problem as a restless multi-armed bandit problem, and a queue scheduling method is proposed to balance priority service provisioning and bursty traffic processing. The proposed queue scheduling method operates efficiently in a timely manner based on instant queue length and utilizes the Whittle index method to achieve an asymptotically optimal solution. This design facilitates packet forwarding by considering the instant states of queues, offering improvements over existing methods. Experimental results demonstrate that the proposed method achieves a more efficient balance between priority service provisioning and bursty traffic processing compared to other state-of-the-art methods. Additionally, the proposed method results in better balanced network performance metrics, such as queue length, packet delay, and packet loss, thus efficiently supporting various applications that generate bursty traffic randomly.

Traffic measurement is essential for network management. Sliding window models can provide network management tasks with flow statistics within the most recent window at any moment. However, most existing solutions over sliding windows are not designed for traffic measurement scenarios, therefore they have higher complexity and cannot be implemented on programmable hardware switches. To address the issues, we designed Ring Sketch, which is a generic, low-complexity, and hardware-friendly traffic measurement framework over sliding windows. Ring Sketch can not only be easily implemented on programmable hardware switches but can also accurately answer typical flow statistics queries by using different sketches. Then we propose the estimation strategies for Ring Sketch and theoretically analyze its error bounds. At last, we implement Ring Sketch on OVS-DPDK and a programmable hardware switch with a Tofino chip, and all the source codes are released on GitHub. The experimental results show that Ring Sketch has a throughput over 3x higher than the state-of-the-art Sliding Sketch, and in typical measurement tasks, Ring Sketch can achieve high measurement accuracy.

Traffic measurement is critical for network manage-ment. The programmable networking paradigm paves the way for implementing fine-grained and accurate traffic measurement. However, in programmable networking, the programmable re-sources on hardware switches are highly limited. Most existing solutions have not considered the deployment of multiple traffic measurement tasks under resource constraints in programmable networks. To address the issue, we construct the network model and problem formulation, and we refer to this problem as the traffic measurement task deployment problem and prove it is NP-hard. To solve it, we proposed an approximate algorithm called Ant Colony Optimization with Dynamic Pruning (ACO-DP). We conducted simulations on the Fat-Tree topologies to evaluate the performance of ACO-DP. The evaluation results show that ACO-DP can achieve much higher overall measurement utility and faster convergence compared to other benchmark algorithms, and the solutions returned by ACO-DP are very close to the optimal solutions.

Federated Learning (FL) is a distributed machine learning method that ensures the privacy and security of participants’ data by avoiding direct data upload to a central node for training. However, the traditional FL typically applies a star structure with cloud servers as the central aggregator for the model parameters from different terminals, leading to problems such as central failure, malicious tampering and malicious participants, resulting in training errors or system crashes. To address these issues, a permissioned blockchain is used to build a secure and reliable data-sharing platform among participating terminals, replacing the central aggregator in the traditional FL called blockchain-based federated learning. However, the block generation method of the blockchain system may introduce significant latency in the federated learning where distributed model parameters upload randomly, resulting in low efficiency of the federated learning. To overcome this, we propose a block generation strategy that groups terminals and generates a block for each group, which minimizes the latency of a single round of federated learning, and an optimal block generation algorithm that considers data distribution, terminal resources, and network resources is provided. The analysis shows that the proposed algorithm can effectively obtain the optimal solution of block generation to minimize the authentication time, and we conduct extensive experiments that demonstrate the time efficiency of the proposed algorithm.

Network function virtualization (NFV) achieves cost-effective network service provisioning through exploitation of virtualization and automation by decoupling network functions (software) from dedicated hardware. The software of the various devices can then be hosted by low-cost general computation devices rather than by more expensive dedicated devices. To obtain a specific network service, the traffic flow is steered to go through a specific order of network functions that are hosted by cloud computing, and this network function sequence is known as a service function chaining (SFC). To allocate computation resources for network functions and bandwidth resources between network functions in a physical network is the SFC embedding problem. In this article, we consider the SFC embedding problem in multi-domain networks, where no domain information, like domain topology and network resource, is disclosed among domains. We propose a new optimization algorithm based on column generation method to solve this problem, which is distributedly computed in each domain. To further improve the scalability, we also provide two heuristic algorithms. We selected two networks one large (158 nodes) and one small (18 nodes) to numerically validate the proposed algorithms and demonstrate that the acceptance ratio obtained by the heuristic algorithms is close (within 5.6 percent) to that of the optimal algorithm.

Network function virtualization (NFV) is a new networking paradigm based on decoupling network functions from dedicated hardware, so these network functions can be run as pieces of software on general-purpose computation servers, which are called virtual network functions. In addition to guarantee the service qualities provided by NFV networks comparable to those provided by traditional telecommunication networks, energy consumption becomes one of the challenges faced by NFV. This is due to a large number of general computation servers that consume a significant amount of energy. We address here the problem of how to provide an energy-aware service function chaining (SFC) embedding in NFV networks with a hierarchical resource allocation, where an SFC has a set of virtual network functions to be executed in a specific sequential order providing a specific network service. Assuming a dynamic traffic scenario, we introduce for this new problem an integer linear programming (ILP) and three polynomial heuristic algorithms for resource allocation. All three heuristic algorithms achieve energy savings by shutting down idle devices and balance the tradeoff between energy cost and SFC request acceptance ratio. Numerical results demonstrate the quality of the proposed heuristic algorithms in terms of acceptance ratio by comparing them with the ILP method and a method extended from an exiting algorithm despite the fact that they save energy.

Edge computing is an indispensable technology that overcomes delay limitations of cloud computing. In edge computing, computational resources are deployed at the network edge, and computational tasks and data of end terminals can be efficiently processed by edge nodes. Considering the computational resource limitations of edge nodes, collaborative edge computing integrates computational resources of edge nodes and provides more efficient computing services for end terminals. This article considers a computation offloading problem in collaborative edge computing networks, where computation offloading and resource allocation are optimized by means of a collaborative load shedding approach: a terminal can offload a computing task to an edge node, which either can process the task with its computing resource or further offload the task to other edge nodes. Long-term objectives and long-term constraints are considered, and Lyapunov optimization is applied to convert the original nonconvex computation offloading problem into a second problem that approximate the original problem and it is still nonconvex but has a special structure, which gives rise to a new distributed algorithm that optimally solves the second problem. Finally, the performance and provable bound of the distributed algorithm is theoretically analyzed. Numerical results demonstrate that the distributed algorithm can achieve a guaranteed long-term performance, and also demonstrate the improvement in performance achieved over the case of computation offloading without collaborating edge nodes.

Edge computing is a promising technology that offers data analysis and computing for Internet of Things (IoT) services at the network edge. It has the potential to significantly reduce the latency and improve the reliability of IoT services by allowing computation workloads and local data generated by IoT devices to be offloaded to edge nodes. This paper aims to develop algorithms for efficient provision of both job assignment and resource allocation for edge computing networks. The main objective is to minimize the long-term average of the response time delay subject to constraints on computation resources and power consumption. We apply a drift-plus-penalty based Lyapunov optimization approach to convert the original problem into an upper bound optimization problem. We then relax the latter to a convex optimization problem. Finally, a distributed algorithm based on branch-and-bound approach is provided and the gap between the distributed algorithm solution and the optimal solution of the original problem is theoretically analyzed. Numerical results based on extensive experiments have demonstrated that our distributed algorithm can achieve the required performance of edge computing that supports IoT systems, under static traffic conditions as well as under dynamic environments with time-varying traffic.

Segment Routing (SR) is an emerging source routing based tunneling technique, which allows source router to steer traffic by encoding segment list in the packet header. Due to its fine-grained control of routing path, SR can be leveraged to facilitate the deployment of Service Function Chains (SFCs). Using SR, multiple segments compose a specific path delivering traffic along a set of ordered Virtual Network Function (VNF) instances. However, when introducing SR into VNF chaining, the segment list depth of SR may face the scalability problem since traffic flows must be steered to traverse a serial of ordered VNFs. To address this problem, we study on segment routing optimization for VNF chaining. Our objective is to minimize the packet overhead of SR for all SFC demands, which indicates the scalability performance of SR. We first formulate the problem as an Integer Linear Programming (ILP) model. Since the ILP model is NP-hard, we then propose a heuristic algorithm named Segment Routing for SFC Steering (SR-SFCS), which is based on the method of backtracking and dynamic programming. Extensive simulation results show that compared with the benchmark algorithms, SR-SFCS can reduce the packet overhead by 23.77% in average.

In Software Defined Networks (SDN), applications on the controller could enforce fine-grained control on flows by policies employing more packet fields. These policies are converted to flow entries and stored in switch Flow Table. To store these entries, Flow Table requires large storage space because an entry consisted of more packet fields needs more storage space and the number of entries also increases significantly due to fine-granularity definition of flows. However, Flow Table has limited storage space owing to the constraints of Ternary Content Addressable Memory (TCAM). As a result, the switch Flow Table in SDN faces scalability issue. We address this issue by means of adaptive Flow Table management, namely we manage how long the entries occupy the storage space by setting adaptive timeouts to them. Through this means, the storage space could be reused efficiently and more flows could be supported with the same Flow Table (without updating hardware devices). Our proposed method TimeoutX, for the first time, combines traffic characteristics, flow types and Flow Table utilization ratio to decide the timeout of each entry and it outperforms current timeout setting strategies in both metrics of table miss number and blocked packet number, which indicates TimeoutX could make the best of Flow Table and support more flows.

In Software Defined Networks (SDN), more packet fields are included to design fine-grained policies. These policies are stored as entries in switch Flow Table. However, fine-grained policies cause the scalability issue as a single flow entry needs larger storage space and a significant number of flow entries need to be stored, but the Flow Table is limited due to the constraints of Ternary Content Addressable Memory (TCAM). To address this issue, we propose Adaptive Hard Timeout Method (AHTM) to improve the Flow Table utilization by optimizing the timeouts of flow entries, thus the Flow Table is reused efficiently. AHTM models the Flow Table as a queueing system and derives closed-form formulas for analysis and optimization. We also implement AHTM as a light-weighted SDN application and it offers interfaces to other applications. The simulation results show that AHTM can achieve the balance between blocking probability and extra workload to SDN controller.

This paper proposes a multicast traffic grooming scheme for efficient resource utilization in wavelength- division multiplexing (WDM) mesh networks. This Light-Tree Division -Adjacent Node Component based Grooming scheme (LTD-ANCG) is based on the idea of dividing a light-tree into smaller sub-light-trees. It improves the efficiency of resource utilization and lowers the optical- electronic-optical (OEO) conversion overhead. We use computer simulations to evaluate the performance of the scheme. Our simulations demonstrate that compared with existing algorithms, the new scheme significantly reduces the request blocking probability but can be implemented with very reasonable electronic processing.