The Traveling Salesman Problem (TSP), a well-known NP-hard problem, is widely applied across manufacturing, biology, transportation, and other fields. In recent years, deep reinforcement learning (DRL), particularly DRL based on Transformer architectures, has emerged as a popular approach to solving TSP. However, the quadratic computational and space complexities of Transformer models pose challenges for handling larger-scale TSP instances. This paper introduces Sym-Favformer, an end-to-end DRL method based on symmetry regularization in the Transformer. In this approach, the encoder incorporates a Fast Attention Via positive Orthogonal Random features (FAVOR+) mechanism with linear complexity, while the decoder adopts a distance-based dynamic selection mechanism, and employs the Lion optimizer to reduce training time and memory consumption. To enhance performance and generalization, Sym-Favformer applies a random transformation data augmentation technique within the encoder and introduces enhanced context embedding in the decoder. Subsequently, the model is trained using a symmetry-regularized REINFORCE method. Experimental results show that Sym- Favformer significantly outperforms existing end-to-end DRL methods on both randomly generated benchmark instances and TSPLIB datasets, demonstrating strong generalization to larger-scale TSP instances.

Link delay is a key factor to evaluate and ensure the stringent network service quality required by the Industrial Internet of Things (IIoT). Because link delay is seriously affected by traffic, obtaining link delay features associated with network traffic is important. This article presents a traffic-associated link delay learning solution for the IIoT. In our solution, the network of the IIoT is divided into many local networks and a software-defined network (SDN). Our solution uses low-loaded methods to collect traffic-delay samples, and uses a traffic-interval-based mechanism to solve the traffic-associated delay statistics problem. We present a link traffic-delay model learning method for local networks of the IIoT. This method uses path traffic-delay samples, independent from specific network paradigms. Our solution uses a particular deep neural network structure to explore the information implied in path traffic-delay samples. We also propose a link traffic-delay model learning method for the SDN, which selects source links by a feature-similarity-based method and generates link traffic-delay models based on transfer learning. Our solution evaluates the accuracy of link traffic-delay models, and further improves the models with low accuracy.

In the Industrial Internet of Things, it is necessary to reserve enough bandwidth resources according to the maximum traffic peak. However, bandwidth reservation based on the maximum traffic peak leads to low resource utilization. In this paper, we propose a data transfer optimization solution, based on the cooperation of different entities in the local area, which strives to deliver data acquired by sensors to the cloud in a reliable manner and improve bandwidth utilization to save limited network resources. In our solution, the data transfers from the sensors in a local network are controlled by a local controller and some edge gateways with acceptable cost such that no congestion occurs in the path to the cloud and the bandwidth requirement of each flow can be met. To obtain a tradeoff between resource utilization and transfer delay, we study the problem of minimizing the maximum rate peak of periodic real-time traffic from distributed sensors and propose an algorithm to solve this problem with a desirable lower boundary of the performance. In addition, we design an application-level forwarding method that significantly improves resource utilization and a method of implementing reliable sampling instant adjustment. The experimental results show that our solution significantly improves resource utilization without producing network congestion.

In addressing the multi-path problem of cloud-edge data transmission, this paper introduces a multi-path orchestration method based on deep reinforcement learning (DRL) within the context of software-defined networks (SDN), termed Deep Q-Routing (DQR). This method establishes optimal data transmission paths between the cloud and multiple edges, based on available bandwidth and transmission delay, while avoiding path congestion to improve bandwidth utilization and reduce transmission delay. The optimal routing in SDN is defined through the design of state space sets, reward functions, and neural networks. Simulation experiments were conducted to evaluate the DQR method. Compared to existing routing methods, the proposed DQR method, which includes a reward function with weighted parameters, demonstrates superior overall network performance.

Despite the development of mobile networks, it is still challenging for current mobile networks to cope with enormous amounts of vehicle video traffic. In this paper, we present a video delivery solution, which is designed to provide steady video content delivery for high-speed vehicles. Our solution improves the steadiness of the video deliveries to vehicle users by a multi-path concurrent delivery mechanism and a path-based content pre-caching mechanism. The concurrent content delivery and content pre-caching can shorten the whole delivery time. However, it sometimes brings heavy stress to the network if the advanced delivery is not controlled. We propose a distributed delivery rate control method to solve the above problem. By the proposed content pre-caching mechanism, each basestation caches appropriate video chunks such that these cached chunks can be used with high probability when the vehicle is within the coverage of the basestation.

Delays are crucial factors in the service management of networks, especially software-defined networks. Unfortunately, it is very difficult to accurately model a traffic-delay mapping without any assumptions on an uncertain network. In this article, we present a machine learning-based solution to generate a mapping between link traffic and link delay in software-defined networks. The proposed solution only requires a small number of link delay samples from the production network. The small number of link delay samples is not sufficient for learning link traffic-delay mapping. To solve the above problem, we extend the link delay-related data via a sample transfer method and a distributed path delay data collection method without the assistance of the controller. We design a link traffic-delay mapping learning solution using the above three classes of data. This solution uses a traffic segment-based statistical mechanism to deduce the mean link delay effectively from the collected path delay information and implements effective sample transfer via a distance-based approximation. On the basis of specially designed deep learning structures and training procedures, the proposed learning solution effectively builds traffic-delay mapping models using the samples transferred from an experimental network and the samples of the production network.

In traditional networks, the multicast tree packing solutions usually aim to minimize the overall multicast tree cost, which can effectively improve network accommodation capacity but is disadvantageous to fully use network resources. In this article, we propose a delay-optimized multicast tree packing problem called delivery delay minimized multicast tree packing (DDMMTP), which aims to minimize the average source-destination delay, under constraints on the bandwidth and maximum source-destination delay, according to available network resources. A low source-destination delay is desirable because it improves the service quality, especially for time-sensitive applications. In practice, the DDMMTP is highly valuable for the software-defined network (SDN) mainly because this new network paradigm has the ability to rapidly rearrange multicast routes on demand. The DDMMTP problem is NP-hard. We solve it approximately by a batched multicast tree packing algorithm and a network accommodation capacity improvement algorithm that adjusts existing multicast paths on demand. We also propose a source-destination delay improvement algorithm to further reduce source-destination delays based on new available network resources.

In view of semantic counterfeiting characteristics of phishing websites and their multi-scale composition, this paper fully considers the semantic information of different scales, and proposes three semantic-based phishing detection models at different depths using various deep learning methods. The proposed three models are Multi-scale Data-layer Fusion (MDF) model, Multi-scale Feature-layer Fusion (MFF) model and Multi-scale In-depth Fusion(MIF) model. Experimental results on a constructed complex dataset show that the three models all have good recognition capabilities and the MIF model achieves the best performance on a complex dataset, with an F1-Measure of 0.9830, AUC value of 0.9993 and a false positive rate of 0.0047. Then with further comparison with both visual and text methods and an active discovery experiment lasting for 6 months with 3016 phishing websites detected in the real network environment, it is found that the proposed model is both competitive and practical for real detection scenarios.

Bandwidth reservation can effectively improve the service quality for data transfers because of dedicated network resources. However, it is difficult to achieve a desired tradeoff between resource utilization and reliable bandwidth guarantees for data transfers with time-varying traffic. In this article, we study a novel bandwidth reservation solution based on distributed traffic monitoring and control for applications that require reliable bandwidth guarantees. In the proposed solution, designated bandwidth is allocated for an application in advance according to its maximum traffic peak, and idle reserved bandwidth resources are dynamically shared according to regular traffic. Dynamic resource sharing evidently improves resource utilization and effectively eliminates the potential congestion caused by sudden traffic bursts. To ensure that the congestion that occurs occasionally can dissipate rapidly, our solution monitors and manages traffic by a distributed monitoring and control strategy. Hence, we study a delay-constrained and proxy-assisted traffic monitoring structure construction problem and propose an algorithm to solve it. The proposed algorithm can also be used to build a delay-constrained traffic control structure. In addition to the above algorithm, we propose a dynamic traffic control algorithm that can achieve a desirable tradeoff between resource utilization and congestion avoidance capability.

Monitoring packet losses at links is beneficial to network management and service quality improvement. Software-defined networking can conveniently obtain flow statistics. However, the packet loss rate of a link or path cannot be directly measured by acquiring the statistics of an ongoing flow. In addition, monitoring the packet loss directly based on statistics inquiries brings considerable extra overhead to the controller. In this paper, we propose a two-way link-level packet loss monitoring solution for the software-defined networks. We propose a packet loss probe structure consisting of distributed rings. The proposed probe structure contains every monitored directed link once and only once, thereby avoiding the mutual interference between different probe flows and thereby improves probe accuracy. We further study two optimization problems of the ring-based packet loss probe structure. The two problems build probe structures, with minimal maximum ring delay, for all the network links and selected network links. The two optimization problems are very complex, and we approximately solve them in polynomial time. A packet loss positioning algorithm, based on flow statistic inquiries and the symmetry design of probe rings, is also proposed. Our proposed solution can effectively monitor link-level packet loss but brings low and controllable overhead to the controller.

Computer Supported Cooperation Work (CSCW) has been playing an increasingly important role in many areas of human social life. Cooperative design refers to the technique of product design based on CSCW and parallel engineering. With widespread use of CSCW, network bandwidth is becoming a bottleneck that affects user experience and service quality. Currently, global attention has been paid to the fifth-generation communication system (5G). In order to address the network bottleneck of the cooperative design system using the 5G network advantages, this paper focuses on optimizing QoE of the cooperative design system and proposes a distributed cache system for cooperative design in the 5G environment. The cache network is divided into different domains based on the characteristics of the 5G structure. Coupling between cache and cooperative design is implemented after taking the properties of the cooperative design system into account. Simulation results demonstrate the ability of the proposed system to considerably improve QoE of the cooperative design system and reduce bandwidth utilization.

Software-Defined Networking (SDN) is an emerging network architecture. SDN is currently attracting significant attention from both academia and industry. A large number of studies have been carried out in academic circles. However, how to build small scale experimental Software-Defined Networking is the basis of various researches. This paper builds a physical device called Xspider for building real SDN experimental environment based on NetFPGA with OpenFlow support. Xspider has the characteristics of saving space, being easy to carry, and the ability to simulate multiple topologies. This kind of physical device can facilitate the application of SDN teaching and experiment, which is beneficial to promote the technological progress of SDN.

Traditional group multicast routing (TGMR) is well known for its difficulty. The technology of network coding bring a new light to this problem. This paper addresses the network coded group multicast routing problem (NCGMR). We propose a hierarchical decomposition model for the minimum cost routing of NCGMR, implement the model in a distributed fashion and extend the model to 0-1 linear programming for TGMR. Finally, we prove that our approach is feasible and evaluate its convergence performance by a numerical example.

Multi-commodity multicast has a wide variety of applications in today's Internet and consumes a large amount of bandwidth resource. In this paper, we propose a two-level decomposition (TLD) model for multi-commodity multicast. Since network coding is allowed, the proposed model can achieve minimum-cost traffic engineering in the presence of uncontrolled traffic. In addition, all the generated subproblems can be computed in parallel or implemented in a distributed manner.

Packet loss rate is an important consideration in the Quality of Service (QoS) measurement for a packet-switched network. The software-defined networking (SDN) technique can conveniently monitor flow statistics. However, the packet loss rate of a link or path cannot be directly measured by inquiring the statistics of an ongoing flow at the starting and ending points because it is impossible to accurately compute and control pairwise sampling moments. In this paper, we propose a two-way link-level packet loss measurement solution for software-defined networks. We solve the flow statistics sampling problem mentioned above by inquiring the statistics of a terminated probe flow. We propose a ring-based packet loss probe structure, which contains every measured directed link once and only once. The proposed probe structure effectively avoids the mutual interference between different probe flows, and thereby improves probe accuracy. The ring is implemented based on the flexible flow match capability of SDN. We further study an optimization problem of ring-based packet loss probe structure that strives to minimize the maximum delay of rings. This optimization problem is very complex, and we approximately solve it using a top-down-top graph partition method. A packet loss positioning method, based on flow statistic inquiries and the symmetry design of the probe ring, is also proposed herein.

Application layer multicast (ALM) is an effective group communication method. The ALM tree is usually built in a distributed manner because of its good scalability. However, the distributed ALM solution sometimes produces a low performance delivery tree. In this paper, we propose an ALM tree optimization solution, named ALMTO, for multicast applications, in particular, those with a large number of concurrent users. ALMTO manages and optimizes the ALM tree in the following four steps: 1) periodic collection of related structure information, based on a proposed structure report domain model and special tree structure; 2) construction and maintenance of a logical ALM tree, in terms of the collected structure information; 3) central computation of the ALM tree optimization scheme, according to the logical ALM tree and optimization objective corresponding to the specific multicast application; and 4) reshaping of the real ALM tree in terms of the optimization scheme. We analyze the problem of the centralized tree optimization scheme orchestration and present an effective solution that can adapt to the dynamics of group members. We also present two approaches: 1) degree-bounded connection-keeping tree transformation and 2) ring-based data compensation to ensure that the ALM tree can be reliably transformed.

Most application layer multicast (ALM) protocols build the delivery tree by the distributed way, which is necessary for large-scale group applications because of its good scalability. However, it is difficult for the distributed way to obtain high performance. To address the above problem, we study a VM-assisted ALM tree optimization solution (called ALMTO). The proposed solution uses cloud virtual machines (VMs) to collect the structure information on the ALM tree, and uses a centralized way to effectively reduce average latency of the ALM tree built by the distribute way.

Robust statistical learning based web spam detection system often requires large amounts of labeled training data. However, labeled samples are more difficult, expensive and time consuming to obtain than unlabeled ones. This paper proposed link based semi-supervised learning algorithms to boost the performance of a classifier, which integrates the traditional Self-training with the topological dependency based link learning. The experiments with a few labeled samples on standard WEBSPAM-UK2006 benchmark showed that the algorithms are effective.