As the demand for network determinism and reliability grows, researchers are committed to developing higher-level protocols or entirely new network protocol stacks. While testing is the most convincing approach, it faces challenges such as scale and budget constraints, making simulation experiments a critical preliminary step. The code utilized for simulation may not be directly transferable to a real-world environment due to compatibility issues with physical devices. Similarly, code developed for physical devices requires thorough test case construction for validation. To tackle this challenge, this paper introduces a lightweight code-reusable platform (CRP) aimed at facilitating the reuse of protocol stack code among various simulation software and operating systems. This framework has been functionally verified on the OPNET and OMNeT++ simulation platforms as well as Linux OS, using test cases from Time-Sensitive Networking (TSN). Experimental results show that the reusable code framework facilitates the migration of protocol code across various platforms with minimal differences in performance, including execution speed, CPU usage, and throughput, in comparison to executing directly.

Unmanned aerial vehicle (UAV) is a promising method for emergency communication due to its rapid deployment and flexible networking. However, the limitations of energy capacity and long communication distances between UAVs make it challenging to cover multiple different relief sites and provide continuous and uninterrupted network services. To this end, we propose a multi-UAV swarm planning strategy to solve the issue while minimizing energy consumption. We first propose a multidifferentiated periodic rotational path method to solve the energy capacity constraints of individual UAVs and ensure the stability of swarm services. Then, a dynamic tree strategy is utilized to support the continuous backhaul network of the UAV swarm, based on the distribution of disaster relief sites. Further, an ant colony-based path planning algorithm is designed to optimize the overall energy consumption of UAVs. Simulation results show that the proposed strategy can construct an efficient UAV swarm to support emergency communication and significantly reduce energy consumption compared to benchmarks.

Federated learning (FL) has received considerable attention because it allows multiple devices to train models locally without revealing sensitive data. Well-trained local models are transmitted to a parameter server for further aggregation. The dependence on a trusted central server makes FL vulnerable to the single point of failure or attack. Blockchain is regarded as a state-of-the-art solution to decentralize the central server and provide attractive features simultaneously, such as immutability, traceability, and accountability. However, current popular blockchain systems cannot be combined with FL seamlessly. Since all local models should be collected before aggregation, the latency of FL is determined by the slowest device. The consensus process required by blockchain will increase the latency further, especially, when a large block is required for including the model. Moreover, forever-growing blockchain together with models will take up a lot of storage space, making it impractical to be deployed on lightweight devices. To address these problems, we propose a lightweight blockchain TORR for FL. A novel consensus protocol Proof of Reliability is designed to achieve fast consensus while mitigating the impact of stragglers. A storage protocol is designed based on erasure coding and periodic storage refreshing policy. With erasure coding, we take full advantage of the limited storage space of devices. With the periodic storage refreshing policy, we reduce the requirement for storage. Compared to the common blockchain-based FL system, TORR reduces the system latency, overall storage overhead, and peak storage overhead by up to 62%, 75.44%, and 51.77%, respectively.

Since the advent of the Internet of Things (IoT), exchanging vast amounts of information has increased the number of security threats in networks. As a result, intrusion detection based on deep learning (DL) has been developed to achieve high throughput and high precision. Unlike general deep learning-based scenarios, IoT networks contain benign traffic far more than abnormal traffic, with some rare attacks. However, most existing studies have been focused on sacrificing the detection rate of the majority class in order to improve the detection rate of the minority class in class-imbalanced IoT networks. Although this way can reduce the false negative rate of minority classes, it both wastes resources and reduces the credibility of the intrusion detection systems. To address this issue, we propose a lightweight framework named S2CGAN-IDS. The proposed framework leverages the distribution characteristics of network traffic to expand the number of minority categories in both data space and feature space, resulting in a substantial increase in the detection rate of minority categories while simultaneously ensuring the detection precision of majority categories. To reduce the impact of sparsity on the experiments, the CICIDS2017 numeric dataset is utilized to demonstrate the effectiveness of the proposed method. The experimental results indicate that our proposed approach outperforms the superior method in both Precision and Recall, particularly with a 10.2% improvement in the F1-score.

As a ubiquitous on-policy reinforcement learning algorithm, proximal policy optimization (PPO) has achieved the state-of-the-art performance in both single-agent and cooperative multi-agent scenarios. However, it still suffers from the instability and inefficiency of the policy optimization with the non-strictly restricted likelihood-ratio in clipping strategy. In this work, we propose an activation likelihood-ratio (ALR) for solving this issue. The ALR is restricted by a tanh activation function, and it can be employed in multiple functional clipping strategies. The resulted ALR clipping strategy produces a smooth but precipitous objective curve, which can provide high policy update stationarity and efficiency. The ALR clipping strategy is incorporated into the PPO loss function, thus resulting in the method proximal policy optimization with activation likelihood-ratio (PPO-ALR). The rationality and superiority of the ALR-based target function are proved and analyzed. Moreover, experiments on the Pistonball cooperative multi-agent game show that PPO-ALR produces competitive and superior results compared with the standard PPO, PPO with rollback, and PPO smoothed algorithms, especially its high efficiency and success probability in searching optimal policies in multi-agent environments.

Since the cyclostationarity in vibration signals is the key to judge the rotating machine health state, spectral harmonics-to-interference ratio (SHIR) has been used to construct single node feature learning network (SHIR-based blind deconvolution, BD-SHIR) to realize condition monitoring of machine. However, BD-SHIR still has several obvious limitations, including the need for prior fault information and the tendency to fall into local optimal solutions which will affect its feature learning and state monitoring performance. Therefore, this paper proposes a multi-node feature learning network based on BDSHIR, which does not rely on prior information, multi-node adaptive BDSHIR (MABD-SHIR). It uses each filter in the 1/3 binary tree filter bank to design each initial node (filter) in the learning network correspondingly, and introduces an adaptive fault characteristic frequency (FCF) detection process. Since this initialization can give some filters close to the fault resonant band, iterations starting from these nodes are more likely to detect the precise FCF and converge to the optimal solution. Finally, MABD-SHIR can obtain multiple local optimal solutions, among which the one with the largest SHIR is generally closer to the global optimal solution than the one obtained by BD-SHIR. Simulation and experimental data of defective rotating machinery verify the effectiveness of MABD-SHIR in machinery condition monitoring and fault feature learning.Note to Practitioners—This paper is motivated by the problems that the rotating machine condition monitoring based on BDSHIR is easy to prematurely fall into local optimal solution and requires prior fault information. These problems can be effectively solved by extending BDSHIR from single node structure to multi-node structure and introducing adaptive period detection technique (A-DPT). The core idea is to start iterations from multiple initial filters and to detect the FCF adaptively during each iteration. Multiple features conforming to filtered signals’ SHIR maximization can be finally learned. Therefore, in this paper, MABD-SHIR is proposed, which is equivalent to a multi-node feature learning network. Since the objective function of BD is usually non-convex, MABD-SHIR can obtain multiple local optimal solutions without requiring prior FCFs. This is more likely to achieve a global optimal solution than BDSHIR, which starts iteration from only one initial filter and ends up with one local optimal solution. In addition, the objective function of MABD-SHIR has lower mathematical complexity, which reduces the difficulty of optimization.

With the continued evolution of autonomous driving, the communication demand for in-vehicle networks (IVNs) has dramatically increased, and the traditional IVN solutions have become ineligible for the needs of new in-vehicle applications. Time-sensitive network (TSN) with the characteristics of determinism, low latency, high reliability, large bandwidth, and open industry standards, has been considered as the most promising technology for the next-generation IVNs. This article summarizes the current state and methodologies of in-vehicle TSN research through the following five aspects: 1) Quality of Service (QoS) strategy; 2) reliability; 3) clock synchronization; 4) network planning; and 5) network management. The corresponding research priorities and technical challenges are also addressed, respectively.

To avoid the inconvenience of the deployment of large-scale blockchains, blockchain simulators are used to facilitate blockchain design and implementation. We evaluate state-of-the-art simulators and find that they suffer from low performance and scalability. To build a more general and faster blockchain simulator, we extend an existing blockchain simulator. We add a network module integrated with a network topology generation algorithm and a block propagation algorithm to simulate the block propagation efficiently. We design a binary transaction pool structure and adopt bitwise operations to accelerate the simulation and reduce memory usage. Moreover, we modularize the simulator based on five primary blockchain processes. Significant blockchain elements are implemented in individual modules and can be combined flexibly to simulate different types of blockchains. Experiments demonstrate that the new simulator reduces the simulation time by an order of magnitude and improves scalability, enabling us to simulate more than ten thousand nodes.

The development of 5G pushes the research community to concentrate on more innovative 5G beyond/6G networks to provide instantaneous connectivity to futuristic applications, such as e-health, autonomous vehicles, and entertainment services broadcasting, etc., which leads to a huge traffic data explosion. How to mitigate the traffic congestion and the bufferbloat problem is a formidable task. The interaction between transport congestion control protocol and the radio access network (RAN) buffer management scheme drastically impacts the congestion and bufferbloat problem. In this paper, we aim to study the RAN buffer management problem from a whole new perspective by leveraging emerging Deep Reinforcement Learning (DRL). We propose a model-free approach, RLRBM, which enables the agent to learn the best buffer size tuning policy as human beings learn skills. We simulate several typical scenarios to evaluate RLRBM. Experimental results show that RLRBM achieves best trade-off between high throughput and low latency.

Modeling distributed parameter systems (DPSs) are usually challenging due to their infinite dimension nature and strong nonlinearity. As a result, the commonly used DPS modeling methods often do not represent this kind of DPSs well due to model reduction and its neglect of nonlinear dynamics. Here, a novel spatiotemporal recurrent neural network (SRNN) modeling method was proposed for nonlinear DPSs. Generally, the space neighboring the points in a DPS interact each other by means of energy transfer, also known as spatial dynamics. In this SRNN model, its hidden layer at each time is designed to represent the spatial dynamics using a bidirectional RNN (BRNN). The BRNN has the ability to represent this complex interaction since its neighboring hidden layers are used to represent these adjacent spatial points and using a forward step and a backward step represents the interaction between neighboring hidden layers. Then, with the combination of all hidden layers of the SRNN over time, the temporal dynamics of the snapshots is exhibited and represented. In this way, this SRNN integrates the spatial/temporal dynamics together and is without requirement of model reduction. A solving approach is then proposed to find its solution, and a convergence analysis further proves that the proposed method can effectively reconstruct the nonlinear spatiotemporal dynamics of the nonlinear DPS. The article not only demonstrate the effectiveness of the proposed method, but also demonstrate its superior modeling performance as compared to several common methods.

Burstable billing is widely adopted by colocation data center providers to charge their users for data transferring. This paper proposes a cost-aware traffic management approach for a colocation data center user under burstable billing where it is charged based on the 95th percentile bandwidth usage. To do this, we first develop a tractable mathematical expression to calculate the 95th percentile usage of a user. Then, we develop an optimization problem to maximize the user's surplus based on both deterministic and stochastic predictions of the user's demand. We show that the resulted optimization problem, while non-convex by nature, can be efficiently solved or approximated using a convex program. We also show that the proposed approach can also be applied in a more general scenario where the user gets services from multiple service providers. Using real-world workload traces, we show that the proposed approach can reduce a colocation data center user's IP transit cost by 26 percent and increase its total surplus by 23 percent, compared to the current practice of allocating bandwidth on-demand.

The emergence of computation intensive and delay sensitive on-vehicle applications makes it quite a challenge for vehicles to be able to provide the required level of computation capacity, and thus the performance. Vehicular edge computing (VEC) is a new computing paradigm with a great potential to enhance vehicular performance by offloading applications from the resource-constrained vehicles to lightweight and ubiquitous VEC servers. Nevertheless, offloading schemes, where all vehicles offload their tasks to the same VEC server, can limit the performance gain due to overload. To address this problem, in this paper, we propose integrating load balancing with offloading, and study resource allocation for a multiuser multiserver VEC system. First, we formulate the joint load balancing and offloading problem as a mixed integer nonlinear programming problem to maximize system utility. Particularly, we take IEEE 802.11p protocol into consideration for modeling the system utility. Then, we decouple the problem as two subproblems and develop a low-complexity algorithm to jointly make VEC server selection, and optimize offloading ratio and computation resource. Numerical results illustrate that the proposed algorithm exhibits fast convergence and demonstrates the superior performance of our joint optimal VEC server selection and offloading algorithm compared to the benchmark solutions.

The emergence of computation intensive on-vehicle applications poses a significant challenge to provide the required computation capacity and maintain high performance. Vehicular Edge Computing (VEC) is a new computing paradigm with a high potential to improve vehicular services by offloading computation-intensive tasks to the VEC servers. Nevertheless, as the computation resource of each VEC server is limited, offloading may not be efficient if all vehicles select the same VEC server to offload their tasks. To address this problem, in this paper, we propose offloading with resource allocation. We incorporate the communication and computation to derive the task processing delay. We formulate the problem as a system utility maximization problem, and then develop a low-complexity algorithm to jointly optimize offloading decision and resource allocation. Numerical results demonstrate the superior performance of our Joint Optimization of Selection and Computation (JOSC) algorithm compared to state of the art solutions.

Traffic engineering (TE) plays an important role in determining the network performance and reliability, which has been studied thoroughly in past decades. However, due to the advances in cloud and mobile computing, the confliction of bandwidth provision and consumption in network becomes more and more complicated. A major challenge of the Infrastructure Provider (InP) is how to guarantee the high-priority user demands, select valuable and appropriate low-priority user demands, and keep maximum profit simultaneously. This kind of optimal problems related with cross- priority TE was studied in this paper. We first analyzed the relationship between network resources, multi-priority user demand and provider's revenue. And then constructed an event- driven SDN-like control system that could support multiple priority TE. Based on the parameters of network topology, SLA and system measurement, an optimal model for InP's profit was given. By building a genetic-based algorithm called global resource allocating (GRA) algorithm, we exploited the near optimal profit that satisfied partial low-priority demands after satisfying all high- priority demands. Moreover, a dual GRA (DGRA) algorithm which can find out optimal mixture deployment patterns was also studied. With numerical results, we show that both GRA and DGRA could always obtain better result compared to a two-step greedy.

Almost all of the state-of-the-art object detectors employ convolutional neural network (CNN) to extract feature. However, how to fully utilize spatial information is a challenge. In this paper, we propose an effective framework for object detection. Our motivation is that multi-scale representation and context are extremely important for object detection. For multi-scale representation, our mothed combines hierarchical feature maps to a fusion map, which has abundant spatial information and high-level semantics. For context, we exploit spatial information by stacking multi-region feature maps. The network is learned end-to-end, by minimize an objective function. Our network achieves competitive results, 75.9% mAP on PASCAL VOC 2007, 72.0% mAP on PASCAL VOC 2012 and 23.2% mAP on MS COCO. The speed of the network is 10 fps. Our studies demonstrate that multiscale representation and context can further improve performance of object detection.

Geographical load balancing (GLB) is widely established by cloud providers, to exploit the differences in electricity price, local green energy generation, transmission delay and cost etc across geographically dispersed data centers (DCs). With GLB, a cloud provider can achieve reduction of electricity cost or/and bandwidth cost or/and delay cost. However, these objectives are not independent from the others. In this paper, we first build an offline optimization-based framework to explore the trade-off among these three objectives under an emerging practical scenario, where the DCs are charged by peak pricing and burstable billing for energy consumption and bandwidth usage, respectively. It turns out that minimizing a specified cost may result in remarkable increases of other costs. Then, we propose a short-term prediction based mechanism (SPM) for the cloud provider to periodically deduce the request distribution strategies. With real-world data traces, we show that SPM can always obtain a suitable trade-off among different costs.

Demand response is widely employed by today's data centers to response to the increasing of electricity cost. To incentivize users of data centers participate in the demand response programs, i.e., breaking the split incentive hurdle, some prior researches proposed market-based mechanisms such as dynamic pricing and static monetary rewards. However, these mechanisms are either intrusive or unfair. In this paper, we use time-varying rewards to incentivize users of data centers grant time-shifting of their requests. With a game-theoretic framework, we model/analyze the game between a single data center and its users. Further, we extend our design via integrating it with another emerging practical demand response strategies: server shutdown or local renewable energy generation. With real-world data traces, we show that a data center with our design can effectively shed its peak electricity load and overall electricity cost without reducing its profit, when compared with the current practice where no incentive mechanism is established.

Data centers spend millions of dollars on their electricity bills annually. Therefore, there is an interest among data center operators to control the electricity usage so as to minimize energy expenditure. However, when it comes to cloud data centers, the electricity usage is mainly controlled by the tenants. Yet, since most cloud data centers charge their tenants with flat rates, the tenants do not have incentives to change their electricity usage to contribute in cutting electricity bills by participation in demand response. Accordingly, in this paper, we propose a game-theoretic framework together with a time varying pricing (TVP) mechanism for cloud data centers to charge their tenants. In this approach, the TVP propagates the actual energy bill, which comprises both demand and energy charges, onto tenants' service costs. As an extension to this core idea, the time- varying amount of renewable energy generated by data center's on-site renewable generators is also taken into account to affect the payments. Our proposed pricing method is evaluated under various experimental data and simulations. We show that TVP can boost data center's profit by 8.2% and reduce the energy bill by 33.0% and improve tenants' aggregate surplus by 12.3%, when comparing it with a flat rates model that uses a widely employed billing method in today's cloud data centers.

Generally, data center's applications have different Quality of Service (QoS) requirements. Meanwhile, data center's tenants may give different priorities to performance and cost. Therefore, it is unsuitable to treat applications/tenants equally. In this paper, we adopt Dynamic Pricing (DP) to charge for the usage of bandwidth and provide tenants with capability to automatically response to the dynamic price. Further, for applications with tight delay requirements, we propose Dynamic Pricing with Bandwidth Reservation (DPBR), which can reserve bandwidth for specific applications. With the modelling of user satisfaction of cost and performance, we show that tenants with DP and DPBR can get better trade-offs between performance and cost. Comparing with Flat Pricing (FP), which is a representative of today's on-demand purchase option, we demonstrate that DPBR is a better option for tenants since it can maximize their satisfactions. The validity is demonstrated through numerical studies and simulations.

Data Center Traffic has the nature of diversity, variability and unpredictability. Due to the varying link state, the network bandwidth value changes. Traditionally, most of the t cloud providers employ static strategies based on predicting or pre-testing tenants' traffic characteristics [5] [8] [6]. Since no perfect traffic prediction methods have been proposed so far, these static methods result in unsatisfactory resource utilization and unreasonable cost. Therefore, this paper aims at designing a decentralized resource allocation method and a dynamic pricing policy based on network state and tenant demands. We can achieve work conservation and adaptability pricing with our network architecture. The simulation results show that DistributedNet can provide performance isolation, differentiated service and min-bandwidth guarantee.

Value at Risk (VaR) measures the worst expected loss of a portfolio over a given horizon at a given confidence level. It summarises the financial risk a company faces into one single number. Recent methods of VaR estimation use parametric conditional models of portfolio volatility to adapt risk estimation to changing market conditions. However, more flexible methods that adapt to the underlying data distribution would be better suited for VaR estimation. In this paper, we consider VaR estimation by using probabilistic fuzzy systems, a semi-parametric method, which combines a linguistic description of the system behaviour with statistical properties of data. The performance of the proposed model is compared to the performance of a GARCH model for VaR estimation. It is found that statistical back testing always accepts PFS models after tuning, while GARCH models may be rejected.

In this paper we present a novel efficient energy-aware approach for clustering nodes in wireless sensor networks. We use different cluster head (CH) declaration delays for each node to characterize the qualification to be a CH. The approach guarantees the fairly uniform cluster distribution while incurring low overheads. Additionally, we do not make any assumptions about the distribution or node capabilities, e.g., location-awareness. The simulation results show that our clustering approach outperforms LEACH both in cluster characteristics and in the efficiency of prolonging the network lifetime.