Erroneous traffic – packets that fail to establish valid bidirectional communication – provides useful signals of misconfigurations, failures, and attacks, but is noisy and rapidly evolving, making systematic analysis challenging. We present EAGLE, an Erroneous traffic Analysis framework using Graph representation LEarning. EAGLE models erroneous traffic as dynamic bipartite graphs between external senders and internal destination ports. EAGLE combines a self-supervised inductive GraphSAGE encoder with a GRU-based temporal model and learns sender representations via graph reconstruction, requiring no labelled data. We evaluate EAGLE on seven days of traffic collected from a /16 university campus network, which contains 155 K external senders and 3 B packets. Across anomaly detection, supervised classification, and clustering, EAGLE consistently outperforms baselines, achieving up to 16.2% ROC AUC and 17.2% macro F1-score improvements. Case studies further demonstrate its ability to uncover coordinated behaviours, highlighting temporal graph representation learning as an effective approach for erroneous traffic modelling.

Nonterrestrial networks (NTNs) enabled Internet of Things (IoT) extends connectivity to remote and underserved areas, enhances network reliability and coverage, and supports diverse IoT applications in challenging environments, such as rural, maritime, and disaster-stricken regions. As an emerging and fast-evolving IoT scheme, NTN-enabled IoT requires extensive evaluation to ensure effective deployment in real-world scenarios, such as connectivity, performance, and security evaluation. Since conducting testing in remote and diverse environments is logistically challenging and costly, we propose a generative artificial intelligence (GAI)-based synthetic traffic generation framework that facilitates comprehensive traffic analysis and performance evaluation. The proposed framework employs a GAI model to learn the traffic pattern and generate synthetic traffic from historical data. Our approach includes an embedding-based model for representing network flow attributes and a conditional generative adversarial network (CGAN) for generating traffic flows. Considering both source-destination information and statistical features achieves more comprehensive characterization of traffic flows. Finally, the simulation results demonstrate that the proposed approach can generate high quality traffic that conforms to real data distribution and shows obvious difference between multiple applications.

The Digital Twin Network (DTN) establishes a real-time virtual mirror of physical networks. Data collection plays an essential role in DTN, which collects the status data of physical network for building highly consistent digital twins. In this paper, we present a network-wide data collection scheme based on In-band Network Telemetry (INT). To build a lifelike mirror of the physical network, the probing path set is required to cover all links so that network topology, traffic load, and port-level device information is captured. We present a Latency-aware High-degree Replicated First (LHRF) vertex-cut graph partitioning algorithm to partition the network into several balanced subgraphs while trying to replicate the high-degree vertexes among partitions first. LHRF aims to balance the length and accumulated latency of the probing paths. With shorter and stabler probing latencies, the information received by digital twin can reflect the latest and consistent network-wide status. To prevent the packets from being fragmented due to overlong paths, a deep limited search (DLS) based path planning algorithm is employed to generate non-overlapped probing paths covering all edges in the separated subgraphs. Simulation results demonstrate that the proposed scheme generates more balanced INT paths with constrained path length and shorter, stabler probing delay.

The Digital Twin Network creates a real-time virtual reflection of the physical network, providing a valuable experimentation and verification platform. To achieve high-fidelity reconstruction of the physical network, adopting a comprehensive, efficient, and high-precision data collection method is necessary. This paper presents a network-wide data collection scheme based on In-band Network Telemetry (INT). However, covering the entire network with a single probing path can result in unnecessarily lengthy paths, while using paths with too large deviation reduces collecting efficiency. Based on graph Community Detection (CD), we propose Graph Partition-based INT (GP-INT) to address these issues to create balanced sub-graphs of network topology. To avoid packet fragmentation due to excessively long paths, a path planning algorithm based on Deep Limited Search (DLS) is further introduced to generate probing paths in separated subgraphs. The proposed scheme is then implemented in P4-defined switches. Simulation results indicate the scheme produces a more balanced and less redundant set of multiple probing paths for network-wide data collection across various network structures.

Federated learning (FL) in Industrial IoT (IIoT) facilitates collaborative model training across distributed edge devices, ensuring data privacy and localized insights without centralized data aggregation. However, the networked parameter sharing mechanism in FL renders it vulnerable to exploitation by man-in-the-middle (MITM) attackers, potentially disrupting the model training process. To mitigate this threat, this article presents a novel blockchain-reinforced FL architecture aimed at enabling cooperative intrusion detection. Initially, FL is leveraged to aggregate all learned information from edge servers, thereby disseminating extracted attack characteristics to all participants through gradient sharing. Subsequently, a blockchain-based parameter verification scheme is introduced to safeguard against tampered local parameters affecting the global model. Clients record model parameters in smart contracts deployed on a private chain, and parameter servers verify parameter confidentiality before aggregation, ensuring only valid parameters are considered. Finally, extensive experiments are conducted using an edge IIoT cybersecurity data set comprising 61 features spanning ten protocol layers and five attacks targeting IIoT connectivity protocols. Simulation results demonstrate that the proposed scheme significantly enhances intrusion detection accuracy, achieving a threefold improvement when two-thirds of federated nodes are subjected to MITM attacks.

Container technologies promise efficient deployment of distributed services, but their potential is hampered by suboptimal resource utilization and network congestion stemming from initial placement decisions made without knowledge of future demands. Existing container cluster management strategies lack robust adaptive capabilities to efficiently balance load as workloads evolve unpredictably over time. This article puts forth the Adaptive Load-aware Container Deployment (ALCoD), a novel container cluster management approach integrating worst fit decreasing heuristic placement with deep Reinforcement Learning (RL)-based migration optimization. ALCoD adapts to fluctuating resource availability and service demands by leveraging the complementary strengths of each technique. The worst fit decreasing approach allows rapid initial cluster deployment when resources are abundantly available, while the deep RL policy orchestrates intelligent container migrations to optimize load balancing during times of resource scarcity, maintaining service availability throughout. Comprehensive evaluations verified that compared to state-of-the-art strategies, ALCoD reduces system response times by 29.19%, improves load balancing by 51.31%, and decreases bandwidth usage by 27.4% under real-world conditions. Beyond these raw performance improvements, ALCoD demonstrates the potential of hybrid algorithms that blend complementary techniques to match the intrinsic dynamics of container clusters. This pioneering approach establishes a solid foundation for realizing the full promise of containerized services through reliable, responsive delivery even as operating conditions continuously evolve.

Developing non-terrestrial networks (NTN) in future wireless networks has been widely recognized to bring advanced communication services to remote and unserved areas. The Low-Earth-Orbit (LEO) constellation has emerged as a promising component for NTN to provide seamless and fast global connectivity. However, since natural dynamic features, the mobility management, in particular the handover (HO) between satellites, plays an important role in ensuring a stable and continuous data service for NTN. Motivated by this fact, this paper proposes a HO optimization strategy based on conditional handover (CHO) mechanism to enhance service continuity in LEO-based NTN. A reward function, related to link service time and service capability, is firstly designed to modify the monitoring conditions of target satellite candidates. The optimal target selection algorithm is proposed to obtain the maximum reward for each CHO. Then, a service continuity performance graph (SCG) model is constructed to predict different potential CHO combinations in service duration. On the basis of SCG, the HO sequence supporting a high-quality and stable data service is predictively calculated for each accessing user. Simulation results demonstrate that the proposed HO optimization scheme can obviously reduce handover rate under different NTN conditions and can better enhance NTN service continuity.

Current cyberspace is confronted with unprecedented security risks, whereas traditional passive protection techniques are ill-equipped for attacks or defects with unknown features. Dynamic heterogeneous redundancy (DHR), a built-in active defense approach, deploys uncertain, random, dynamic systems to change the asymmetry of attack and defense, where arbitration is one of the key mechanisms. In this article, an AI-assisted trustworthy architecture based on DHR and deep reinforcement learning-based intelligent arbitration (DRLIA) algorithm is presented to enhance security for industrial Internet of things (IIoT). A double deep Q network (DDQN) is introduced, which is capable to distinguish the reliable and credible IIoT message from executors through interaction with the DHR environment. Finally, the DRLIA is implemented to conduct arbitration tasks in an IIoT critical message transmission scenario, where several comparison experiments between DRLIA and other traditional algorithms are designed. The result on the testbed empirically demonstrates the effectiveness of the proposed architecture and the security enhancement.

The satellite-terrestrial networks (STN) utilize the spacious coverage and low transmission latency of the Low Earth Orbit (LEO) constellation to transfer requested content for subscribers especially in remote areas. With the development of storage and computing capacity of satellite onboard equipment, it is considered promising to leverage in-network caching technology on STN to improve content distribution efficiency. However, traditional caching and distribution schemes are not suitable in STN, considering dynamic satellite propagation links and time-varying topology. More specifically, the unevenness of user distribution heightens difficulties for assurance of user quality of experience. To address these problems, we first propose a density-based network division algorithm. The STN is divided into a series of blocks with different sizes to amortize the data delivery costs. To deploy the caching satellites, we analyze the link connectivity and propose an approximate minimum coverage vertex set algorithm. Then, a novel cache node selection algorithm is designed for optimal subscriber matching. On the basis of time-varying network model, the STN cache content updating mechanism is derived to enable a stable and sustainable quality of user experience. The simulation results demonstrate that the proposed user-oriented STN content distribution scheme can obviously reduce the average propagation delay and network load under different network conditions and has better stability and self-adaptability under continuous time variation.

The LEO satellite network (LSN) is envisioned to be highly advanced and ubiquitous, as a function complement and enhancement of ground networks. The satellite networking enables low-latency and high-speed data transmission over long distances for global users, especially in remote areas. Since the nature of time-variability, it is not easy to arrange the satellite networking scheme for tasks at each time slot. Specifically, the main problem is how to ensure that the networking scheme always follows the maximum network transmission capacity during the task duration. To address the problem, this paper first constructs a time-varying LSN model to describe the network characteristics. The networking problem is formulated as the maximum network transmission capacity (NTC) problem at each time slot. Next, a two-stage contact optimization scheme is given. The transmission-based depth first search (TDFS) algorithm is first proposed to calculate the optimal networking for each specified time slot. Then a network performance graph (NPG) is constructed to show the NTC performances of different time slot combinations. The dynamic programming is utilized on NPG to find the optimal time slot sequence. Simulation results show that the proposed contact management with dynamic programming (CMDP) scheme achieves better network throughput and service continuity for LSN.

The mobile satellite communication networks (MSCN) enable network expansion and supplement in remote areas. Users in these regions can obtain specific network services with low latency and high transmission rates utilizing the low-earth-orbit (LEO) satellite constellation. However, due to the frequent switching of MSCN topology, the challenge is how to ensure the quality and continuity of data transmission paths in a certain time period. In this paper, we build a user satisfaction (US) indicator to measure the performance of pathfinding. The MSCN pathfinding optimization problem for the maximum US is first formulated. To simplify the complex calculation, we utilize the special-temporal division to solve the problem in two stages. In each time slot, the modified heuristic algorithm is utilized to find paths for the maximum US. Then, an active time slot division scheme is proposed. The divided time slot sequences are disconnected and reorganized to seek the time-extended optimal solution. Simulation results show that the proposed scheme achieves superior performance in improving the total US and guarantees reliable service continuity for MSCN.

Electric vehicles networks have become hot topics in research and industry and played an important role in smart future cities. However, high energy consumption is a significantly challenge for these applications. This article proposes a electric vehicles cloud computing framework to perform energy-efficient heterogeneous networking for electric vehicles network in smart future cities. The software-defined networking ideas is used to enable different devices including electric vehicles to access the cloud computing network for electric vehicles connected. The edge computing is exploited to run quick computing and communication for these application. Then an energy-efficient heterogeneous networking method is presented to overcome high energy consumption. The mixed integer linear programming optimization model and two heuristic models are proposed to perform energy-efficient networking. An networking algorithm is proposed to achieve highly energy-efficient networking for electric vehicles network. The detailed simulation experiments are conducted to validate our approach. Simulation results illustrate that the proposed method is efficient and feasible.

Internet of Vehicles (IoV), which plays a significantly important role in smart future cities, has become current hot research topics. However, the high heterogeneous nature of IoV has brought many new challenges such as low network performance and difficult network management for IoV. Software-defined networking enables the efficient solution of these problem. This article studies the measurement and analysis technology for software-defined networking of IoV. A new software-defined networking-based IoV heterogeneous networking measurement framework is proposed to build software-defined networking of IoV. We propose a performance measurement and analysis method to measure and characterize its performance. The performance indexes and measure methods about the delay, loss, throughput, delay jitter is in detail derived. The switch selection mechanism is proposed to establish optimal measurement points of advantage. The packet sampling process is presented to quickly obtain the needed measurement information from massive traffic flows. To validate our measurement method and fairly characterize its measurement performance for different controllers, we conduct massive simulation experiments to systematically analyze and compare current famous controllers. In such a case, we provide more comprehensive, systematic measurement analysis for application in software-defined networking of IoV. Experiments results show that our measurement approach is feasible and effective.

The space-air integrated networks (SAIN) has been a valuable architecture due to its characteristics of wide coverage and high survey accuracy. However, it is not easy to design routing strategy in SAIN, considering complex relative motion of low-earth-orbit (LEO) satellites and unmanned aerial vehicles (UAV). Specifically, the main problem is how to find optimal links to realize stable and efficient UAV data transmission in time-varying SAIN. To address the problem above, this paper first analyzes the motion characteristics of satellites and UAVs to find the optimal accessing control satellites (ACSs) for the UAV. Then, different from traditional routing, a branch-based link planning strategy (BLPS) is proposed to realize efficient and stable inter-satellite link (ISL) deployment between ACSs, which can guarantee timely transmission of UAV data. Simulation results show that the proposed BLPS strategy is feasible and effective.

With the rapid development of the mobile Internet and the Internet of Things (IoT), the conventional centralized cloud computing environment is facing severe challenges, such as high latency, and low bandwidth which significantly reduces the user experience for the applications of Virtual Reality (VR), HD Video, etc. Mobile Edge Computing (MEC) architecture can shift several tasks to devices on the edge of the mobile network, decreasing the service time and relieving the flow pressure of the core network. Combining Software Defined Networking (SDN) and MEC, this paper proposes a MEC network model based on SDN and builds test models on physical devices. A set of network testing experiments is carried out to evaluate the performance of the topology. Meanwhile, motivated by the demand for quick processing of surveillance video, an intelligent video processing acceleration application is deployed on the testing platform and cloud computing platform. Under the control of a Floodlight controller, it shows that the MEC scheme proposed in this paper has better performance when carrying latency-sensitive services.

Abstract Internet of things (IoT) is a global information infrastructure that supports access to thousands of monitoring devices and user terminals. A large amount of monitoring data generated by IoT is integrated to cloud computing through the network to improve the quality of life of citizens. Fine‐grained and accurate traffic information is important for IoT network management. Software‐defined networking (SDN) is a centralized control plane as a logical control center, making network management more flexible and efficient. Then, we collect fine‐grained traffic information in SDN‐based IoT networks to improve network management. To acquire the traffic information with low overhead and high accuracy, first, we collect the statistics of coarse‐grained traffic of flows and fine‐grained traffic of links, and then we utilize the intelligent optimization methods to estimate the network traffic. To improve the granularity and accuracy of the acquired traffic information, we construct an optimization function with constraints to decrease the estimation errors. As the optimization function of traffic information is a non‐deterministic polynomial‐hard problem, we present a heuristic algorithm to obtain the optimal solution of the fine‐grained measurement. Finally, we conduct some simulations to verify the proposed measurement scheme. Simulation results show that our approach can improve the granularity and accuracy of traffic information with intelligent optimization methods.

We study the problem of the energy-efficient networking in cloud services with geographically distributed data centers for industrial Internet-of-Things (IIoT) networks, specially for multimedia IIoT networks. This is significantly challenged by dynamic end-to-end request demands and unbalanced link energy efficiency, unbalanced and time-varying link utilization, and bandwidth and delay constraints for service requirements. To solve these issues, we propose a multi-constraint optimization model for the energy efficiency optimization in cloud computing services where data centers are geographically distributed and are interconnected by cloud networks. Our model jointly optimizes energy efficiency in data centers and cloud networks. An intelligent heuristic algorithm is presented to solve this model for dynamic request demands between different data centers and between data centers and users. This is implemented by combining the niche genetic algorithm and the random depth-first search. Simulation results for energy-efficient networking show that better gains in network energy efficiency can be achieved by our joint optimization. Joint optimization between industrial data centers and industrial cloud networks can further improve energy savings and link utilization for time-varying requests.

In this article, we propose a big data based analysis framework to analyze and extract network behaviors in cellular networks for Industry 4.0 applications from a big data perspective, using Hadoop, Hive, HBase, and so on. The data prehandling and traffic flow extraction approaches are presented to construct effective traffic matrices. Accordingly, we can capture network behaviors in cellular networks from a networkwide perspective. Although there have been a number of prior studies on cellular network usage, to the best of our knowledge, this article is a first study that characterizes network behaviors using the big data analytics to analyze a network big data of call detail records over a longer duration (five months), with more users (five million), more records (several hundred million lines) and nationwide coverage. The call pattern analysis and network behavior extraction approaches are designed to perform big data analysis and feature extractions. Then, the corresponding algorithms are proposed to characterize network behaviors, i.e., cellular call patterns and network resource usage. The detailed evaluation is proposed to validate our method. For example, we find that some unpopular calls can last longer time and thus consume more network resources.

The distributed energy system is used as the prototype of the energy Internet, including a variety of forms of energy networks, plenty of distributed equipment and energy storage equipment composed of energy flow, and real-time communication and data volume of information systems. As an important energy system that is closely related to people's lives, its security and stability is one of the cores of its development. With the access of a large number of distributed devices, the structure of the power system has changed greatly. The addition of various forms of energy network, distributed equipment, and energy storage equipment has made it more difficult for the energy Internet to achieve the coordination among and control over these devices. Regardless of the fluctuation of the power load and the sudden change of the thermal load, problems such as energy network failure and demand will affect the security and stability of the energy Internet. Traditional energy systems are independent of one another, while integrated energy systems include subsystems, such as the power system, thermal system, and natural gas system, which can complement one another in planning and operation. To improve the utilization rate of all kinds of energy, reduce the waste of energy, and cut the emission of pollutants, it is crucial to realize the economic utilization of energy as well as the safe and stable operation of the energy Internet.

Software Defined Networking (SDN) architecture satisfies the flexibility and scalability requirements of Internet of Things (IoT) network. A large amounts of IoT data is transmitted and exchanged through IoT network. However, many of services of IoT are sensitive to latency and bandwidth, so the network traffic model and measurement in IoT are different legacy networks. In this paper, we propose a robust network traffic modeling approach and use it to estimate network traffic in IoT. To obtain the measurement results with low overhead and high accuracy, we model the network traffic as liner function with noise. Then, we collect the statistics of coarse-grained traffic of flows and fine-grained traffic of links, and use the robust network traffic model to forecast the network traffic with the coarse-grained measurement of flows. In order to optimize the estimation results, we propose an optimization function to decrease the estimation errors. Since the optimization function is NP-hard problem, then we use a heuristic algorithm to obtain the optimal solution of the fine-grained measurement. Finally, we conduct some simulations to verify the proposed measurement scheme. Simulation results show that our approach is feasible and effective.

The low earth orbit (LEO) satellite network has been a valuable architecture due to its characteristics of wide coverage and low transmission delay. Utilizing LEO satellites as edge computing nodes to provide real-time services for access terminals will be the indispensable paradigm of integrated space-air-ground network. However, it is not easy to design resource management strategies in edge computing satellite (ECS), considering different accessing planes and resource requirements of terminals. Moreover, a comprehensive analysis of the network topology, relative motion, and available resources is required to establish ECS collaborative networks. To address these problems, the dynamic resource allocation architecture and advanced K-means algorithm (AKA) in ECSs are proposed. Then, the extended graph model and breadth-first-search-based spanning tree (BFST) algorithm are utilized to guide the inter-satellite link (ISL) construction. As a result, the ECS collaborative network is established with fine-grained resource management. Simulation results show that the proposed fine- grained resource management scheme is feasible and effective.

This paper uses big data technologies to study base stations' behaviors and activities and their predictability in mobile cellular networks. With new technologies quickly appearing, current cellular networks have become more larger, more heterogeneous, and more complex. This provides network managements and designs with larger challenges. How to use network big data to capture cellular network behavior and activity patterns and perform accurate predictions is recently one of main problems. To the end, firstly we exploit big data platform and technologies to analyze cellular network big data, i.e. Call Detail Records (CDRs). Our CDRs data set, which includes more than 1000 cellular towers, more than million lines of CDRs, and several million users and sustains for more than 100 days, is collected from a national cellular network. Secondly, we propose our methodology to analyze these big data. The data pre-handling and cleaning approach is proposed to obtain the valuable big data sets for our further studies. The feature extraction and call predictability methods are presented to capture base stations' behaviors and dissect their predictability. Thirdly, based on our method, we perform the detailed activity pattern analysis, including call distributions, cross correlation features, call behavior patterns, and daily activities. The detailed analysis approaches are also proposed to dig out base stations' activities. A series of findings are found and observed in the analysis process. Finally, a study case is proposed to validate the predictability of base stations' behaviors and activities. Our studies demonstrates that big data technologies can indeed be utilized to effectively capture network behaviors and predict network activities so that they can help perform highly effective network managements.

We study the problem of energy-efficient networking in cloud services with geographically distributed data centers for multimedia big data applications. This is significantly challenged by the dynamic end-to-end request demands and unbalanced link energy efficiency, the unbalanced and time-varying link utilization, and the bandwidth and delay constraints for service requirements. To solve these issues, we propose a multi-constraint optimization model for energy efficiency optimization in cloud computing services where data centers are geographically distributed and are interconnected by the cloud network. Our model jointly optimizes the energy efficiency in data centers and the cloud network. More specifically, we present an intelligent heuristic algorithm to solve this model for the dynamic request demands between different data centers and between data centers and users. This is implemented by combining the niche genetic algorithm and random depth-first search. Simulation results for energy-efficient networking show that better gains in network energy efficiency can be achieved by our joint optimization. Additionally, the joint optimization between data centers and the cloud network can further improve energy savings and link utilizations for time-varying requests.

Cognitive networks (CNs) are one of the key enablers for the Internet of Things (IoT), where CNs will play an important role in the future Internet in several application scenarios, such as healthcare, agriculture, environment monitoring, and smart metering. However, the current low packet transmission efficiency of IoT faces a problem of the crowded spectrum for the rapidly increasing popularities of various wireless applications. Hence, the IoT that uses the advantages of cognitive technology, namely the cognitive radio-based IoT (CIoT), is a promising solution for IoT applications. A major challenge in CIoT is the packet transmission efficiency using CNs. Therefore, a new Q-learning-based transmission scheduling mechanism using deep learning for the CIoT is proposed to solve the problem of how to achieve the appropriate strategy to transmit packets of different buffers through multiple channels to maximize the system throughput. A Markov decision process-based model is formulated to describe the state transformation of the system. A relay is used to transmit packets to the sink for the other nodes. To maximize the system utility in different system states, the reinforcement learning method, i.e., the Q learning algorithm, is introduced to help the relay to find the optimal strategy. In addition, the stacked auto-encoders deep learning model is used to establish the mapping between the state and the action to accelerate the solution of the problem. Finally, the experimental results demonstrate that the new action selection method can converge after a certain number of iterations. Compared with other algorithms, the proposed method can better transmit packets with less power consumption and packet loss.

The emerging technologies for connected vehicles have become hot topics. In addition, connected vehicle applications are generally found in heterogeneous wireless networks. In such a context, user terminals face the challenge of access network selection. The method of selecting the appropriate access network is quite important for connected vehicle applications. This paper jointly considers multiple decision factors to facilitate vehicle-to-infrastructure networking, where the energy efficiency of the networks is adopted as an important factor in the network selection process. To effectively characterize users' preference and network performance, we exploit energy efficiency, signal intensity, network cost, delay, and bandwidth to establish utility functions. Then, these utility functions and multi-criteria utility theory are used to construct an energy-efficient network selection approach. We propose design strategies to establish a joint multi-criteria utility function for network selection. Then, we model network selection in connected vehicle applications as a multi-constraint optimization problem. Finally, a multi-criteria access selection algorithm is presented to solve the built model. Simulation results show that the proposed access network selection approach is feasible and effective.

Wireless mesh network is prevalent for providing a decentralized access for users and other intelligent devices. Meanwhile, it can be employed as the infrastructure of the last few miles connectivity for various network applications, for example, Internet of Things (IoT) and mobile networks. For a wireless mesh backbone network, it has obtained extensive attention because of its large capacity and low cost. Network traffic prediction is important for network planning and routing configurations that are implemented to improve the quality of service for users. This paper proposes a network traffic prediction method based on a deep learning architecture and the Spatiotemporal Compressive Sensing method. The proposed method first adopts discrete wavelet transform to extract the low‐pass component of network traffic that describes the long‐range dependence of itself. Then, a prediction model is built by learning a deep architecture based on the deep belief network from the extracted low‐pass component. Otherwise, for the remaining high‐pass component that expresses the gusty and irregular fluctuations of network traffic, the Spatiotemporal Compressive Sensing method is adopted to predict it. Based on the predictors of two components, we can obtain a predictor of network traffic. From the simulation, the proposed prediction method outperforms three existing methods.

Wireless mesh network is prevalent for providing a decentralized access for users. For a wireless mesh backbone network, it has obtained extensive attention because of its large capacity and low cost. Network traffic prediction is important for network planning and routing configurations that are implemented to improve the quality of service for users. This paper proposes a network traffic prediction method based on a deep belief network and a Gaussian model. The proposed method first adopts discrete wavelet transform to extract the low-pass component of network traffic that describes the long-range dependence of itself. Then a prediction model is built by learning a deep belief network from the extracted low-pass component. Otherwise, for the rest high-pass component that expresses the gusty and irregular fluctuations of network traffic, a Gaussian model is used to model it. We estimate the parameters of the Gaussian model by the maximum likelihood method. Then we predict the high-pass component by the built model. Based on the predictors of two components, we can obtain a predictor of network traffic. From the simulation, the proposed prediction method outperforms three existing methods.

Many researches show that the power consumption of network devices of ICT is nearly 10% of total global consumption. While the redundant deployment of network equipment makes the network utilization is relatively low, which leads to a very low energy efficiency of networks. With the dynamic and high quality demands of users, how to improve network energy efficiency becomes a focus under the premise of ensuring network performance and customer service quality. For this reason, we propose an energy consumption model based on link loads, and use the network’s bit energy consumption parameter to measure the network energy efficiency. This paper is to minimize the network’s bit energy consumption parameter, and then we propose the energy-efficient minimum criticality routing algorithm, which includes energy efficiency routing and load balancing. To further improve network energy efficiency, this paper proposes an energy-efficient multi-constraint rerouting (E2MR2) algorithm. E2MR2 uses the energy consumption model to set up the link weight for maximum energy efficiency and exploits rerouting strategy to ensure network QoS and maximum delay constraints. The simulation uses synthetic traffic data in the real network topology to analyze the performance of our method. Simulation results that our approach is feasible and promising.

This paper studies the routing problem for IP energy-efficient networks. We propose a robust routing algorithm to reach the higher network energy efficiency, which is based on optimization problem. To attain the highly energy-efficient routing for IP networks, the link of low utilization is turned into the sleeping state to save the network energy. At the same time, the low link traffic is aggregated to the link with high utilization to enhance the link utilization and to sleep the links as many as possible. We present an optimized link sleeping method to maximize the number of the sleeping links. By targeting the network robustness, a weight adaptive strategy is brought forth to reduce the link congestion and enhance the robustness of the network. Simulation results indicate that our algorithm is effective and feasible for IP energy-efficient networks.

This paper proposes a constrained iterative optimal approach to estimate traffic matrix, namely all origin-destination traffic, in a large-scale backbone network. Based on the modified principal component analysis method, we denote traffic matrix estimation problem into an iterative optimal process under the constraints followed by it. In each iterative step, the covariance matrix of traffic matrix is used to capture its spatio-temporal correlation in order to make the more accurate estimation. Furthermore, we present an iterative adjustment method to find the optimal solution in accordance with link load deviation yielded by traffic matrix estimation. Thus this will gradually overcome the highly ill-posed nature of this problem and obtain the accurate estimation. Finally, we use the real data from a backbone network to validate our method. Simulation results show that our method is effective and practical.

This paper proposes a novel method of large-scale IP traffic matrix estimation, based on the recurrent multiplayer perceptron (RMLP) network that is a kind of recurrent neural networks. Firstly, we model the large-scale IP traffic matrix estimation using the RMLP network that can well denote the dynamic behavior of IP network. Based on the conventional RMLP network, we present a new multi-input and multi-output RMLP network model. Then by the model, we present a novel approach to the large-scale IP traffic matrix estimation. Finally, we use the real data from the Abilene Network to validate our method. The results show that our method and model can perform well the accurate estimation of traffic matrix and track its dynamics.