TSN Switch Queue Length Prediction Based on an Improved LSTM Network

With the high-speed development of network technology, time-sensitive networks (TSNs) are experiencing a phase of significant traffic growth. At the same time, they have to ensure that highly critical time-sensitive information can be transmitted in a timely and accurate manner. In the future, TSNs will have to further improve network throughput to meet the increasing traffic demand based on the guaranteed transmission delay. Therefore, an efficient route scheduling scheme is necessary to achieve network load balance and improve network throughput. A time-sensitive software-defined network (TSSDN) can address the highly distributed industrial Internet network infrastructure, which cannot be accomplished by traditional industrial communication technologies, and it can achieve distributed intelligent dynamic route scheduling of the network through global network monitoring. The prerequisite for intelligent dynamic scheduling is that the queue length of future switches can be accurately predicted so that dynamic route planning for flow can be performed based on the prediction results. To address the queue length prediction problem, we propose a TSN switch queue length prediction model based on the TSSDN architecture. The prediction process has three steps: network topology dimension reduction, feature selection, and training prediction. The principal component analysis (PCA) algorithm is used to reduce the dimensionality of the network topology to eliminate unnecessary redundancy and overlap of relevant information. Feature selection requires comprehensive consideration of the influencing factors that affect the switch queue length, such as time and network topology. The training prediction is performed with the help of our enhanced long short-term memory (LSTM) network. The input-output structure of the network is changed based on the extracted features to improve the prediction accuracy, thus predicting the network congestion caused by bursty traffic. Finally, the results of the simulation demonstrate that our proposed TSN switch queue length prediction model based on the improved LSTM network algorithm doubles the prediction accuracy compared to the original model because it considers more influencing factors as features in the neural network for training and learning.

A Blockchain-Based Authentication Protocol Using Cryptocurrency Technology in LEO Satellite Networks

With the rapid development of satellite technology and the high transmission efficiency of LEO satellites, LEO satellite communication has received increasing attention. However, the frequent switching of satellite-earth links imposes a great challenge in LEO communication authentication. To tackle this challenge, this paper proposes a Blockchain-based Authentication Protocol Using Cryptocurrency Technology (BAPC), which solves the problem of a long pause time of satellite services caused by user access authentication in a scenario of frequent switching between satellites and ground users. First, we design three stages of the authentication process and introduce the cryptocurrency technology. Using currency transactions as the certificate of authentication improves not only the security of authentication, but also the efficiency of switching authentication. Next, in the network topology, the satellite cluster is divided into multiple regions to improve the efficiency of block consensus. Finally, the protocol is tested through extensive NS2-based simulations, and the results verify that BAPC can greatly shorten the response time of switching authentication and significantly reduce the time of block generation and the network throughput. As the number of users increases, the block generation time and network throughput can be further reduced.

Certificateless Multisignature Scheme Suitable for Network Coding

Network coding can save the wireless network resources and improve the network throughput by combining the routing with coding. Traditional multisignature from certificateless cryptosystem is not suitable for the network coding environment. In this paper, we propose a certificateless multisignature scheme suitable for network coding (NC-CLMSS) by using the sequential multisignature and homomorphic hash function. NC-CLMSS is based on the CDH and ECDL problems, and its security is detailedly proved in the random oracle (RO) model. In NC-CLMSS, the source node generates a multisignature for the message, and the intermediate node linearly combines the receiving message. NC-CLMSS can resist the pollution and forgery attacks, and it has the fixed signature length and relatively high computation efficiency.

Intelligent Resource Allocation Method for Wireless Communication Networks Based on Deep Learning Techniques

In this paper, a deep learning approach is used to conduct an in-depth study and analysis of intelligent resource allocation in wireless communication networks. Firstly, the concepts related to CSCN architecture are discussed and the throughput of small base stations (SBS) in CSCN architecture is analyzed; then, the long short-term memory network (LSTM) model is used to predict the mobile location of users, and the transmission conditions of users are scored based on two conditions, namely, the mobile location of users and whether the small base stations to which users are connected have their desired cache states, and the small base stations select the transmission. The small base station selects several users with optimal transmission conditions based on the scores; then, the concept of game theory is introduced to model the problem of maximizing network throughput as a multi-intelligent noncooperative game problem; finally, a deep augmented learning-based wireless resource allocation algorithm is proposed to enable the small base station to learn autonomously and select channel resources based on the network environment to maximize the network throughput. Simulation results show that the algorithm proposed in this paper leads to a significant improvement in network throughput compared to the traditional random-access algorithm and the algorithm proposed in the literature. In this paper, we apply it to the fine-grained resource control problem of user traffic allocation and find that the resource control technique based on the AC framework can obtain a performance very close to the local optimal solution of a matching-based proportional fair user dual connection algorithm with polynomial-level computational complexity. The resource allocation and task unloading decision policy optimization is implemented, and at the end of the training process, each intelligent body independently performs resource allocation and task unloading according to the current system state and policy. Finally, the simulation results show that the algorithm can effectively improve the quality of user experience and reduce latency and energy consumption.

Transmission Delay-Based Uplink Multi-User Scheduling in IEEE 802.11ax Networks

As the demands for uplink traffic increase, improving the uplink throughput has attracted research attention in IEEE 802.11 networks. To avoid excessive competition among stations and enhance the uplink throughput performance, the IEEE 802.11ax standard supports uplink multi-user transmission scenarios, in which AP triggers certain stations in a network to transmit uplink data simultaneously. The performance of uplink multi-user transmissions highly depends on the scheduler, and station scheduling is still an open research area in IEEE-802.11ax-based networks. In this paper, we propose a transmission delay-based uplink multi-user scheduling method. The proposed method consists of two steps. In the first step, the proposed method makcreateses station clusters so that stations in each cluster have similar expected transmission delays. The transmission delay-based station clustering increases the ues of uplink data channels during the uplink multi-user transmission scenario specified in IEEE 802.11ax. In the second step, the proposed method selects cluster for uplink multi-user transmissions. The cluster selection can be performed with a proportional fair-based approach. With the highly channel-efficient station cluster, the proposed scheduling method increases network throughput performance. Through the IEEE 802.11ax standard compliant simulations, we verify the network throughput performance of the proposed uplink scheduling method.

Self-Organized Efficient Spectrum Management through Parallel Sensing in Cognitive Radio Network

In this paper, we propose an innovative self-organizing medium access control mechanism for a distributed cognitive radio network (CRN) in which utilization is maximized by minimizing the collisions and missed opportunities. This is achieved by organizing the users of the CRN in a queue through a timer and user ID and providing channel access in an orderly fashion. To efficiently organize the users in a distributed, ad hoc network with less overhead, we reduce the sensing period through parallel sensing wherein the users are divided into different groups and each group is assigned a different portion of the primary spectrum band. This consequently augments the number of discovered spectrum holes which then are maximally utilized through the self-organizing access scheme. The combination of two schemes augments the effective utilization of primary holes to above 95%, even in impasse situations due to heavy primary network loading, thereby achieving higher network throughput than that achieved when each of the two approaches are used in isolation. By efficiently combining parallel sensing with the self-organizing MAC (PSO-MAC), a synergy has been achieved that affords the gains which are more than the sum of the gains achieved through each one of these techniques individually. In an experimental scenario with 50% primary load, the network throughput achieved with combined parallel sensing and self-organizing MAC is 50% higher compared to that of parallel sensing and 37% better than that of self-organizing MAC. These results clearly demonstrate the efficacy of the combined approach in achieving optimum performance in a CRN.

Enhancement of network coding in wireless sensor network using improved lion algorithm: intention toward maximizing network throughput and lifetime

PurposeSince communication usually accounts as the foremost problem for power consumption, there are some approaches, such as topology control and network coding (NC), for diminishing the activity of sensors’ transceivers. If such approaches are employed simultaneously, then the overall performance does raise as expected. In a wireless sensor network (WSN), the linear NC has been shown to enhance the performance of network throughput and reduce delay. However, the NC condition of existing NC-aware routings may experience the issue of false-coding effect in some scenarios and usually neglect node energy, which highly affects the energy efficiency performance. The purpose of this paper is to propose a new NC scheduling in a WSN with the intention of maximizing the throughput and minimizing the energy consumption of the network.Design/methodology/approachThe improved meta-heuristic algorithm called the improved mutation-based lion algorithm (IM-LA) is used to solve the problem of NC scheduling in a WSN. The main intention of implementing improved optimization is to maximize the throughput and minimize the energy consumption of the network during the transmission from the source to the destination node. The parameters like topology and time slots are taken for optimizing in order to obtain the concerned objective function. While solving the current optimization problem, it has considered a few constraints like timeshare constraint, data-flow constraint and domain constraint. Thus, the network performance is proved to be enhanced by the proposed model when compared to the conventional model.FindingsWhen 20 nodes are fixed for the convergence analysis, performed in terms of multi-objective function, it is noted that during the 400th iteration, the proposed IM-LA was 10.34, 13.91 and 50% better than gray wolf algorithm (GWO), firefly algorithm (FF) and particle swarm optimization (PSO), respectively, and same as LA. Therefore, it is concluded that the proposed IM-LA performs extremely better than other conventional methods in minimizing the cost function, and hence, the optimal scheduling of nodes in a WSN in terms of the multi-objective function, i.e. minimizing energy consumption and maximizing throughput using NC has been successfully done.Originality/valueThis paper adopts the latest optimization algorithm called IM-LA, which is used to solve the problem of network coding scheduling in a WSN. This is the first work that utilizes IM-LA for optimal network coding in a WSN.