Machine Learning–Based Mobility Robustness Optimization Under Dynamic Cellular Networks

Due to the constantly moving of the communication nodes in the combat environment, the network topology is highly dynamic and uncertain. However, combat missions require the real-time and accurate information transmission through the military network. Therefore, it is of great practical interest to design a dynamic routing algorithm to accommodate to the dynamic and uncertain network topology. We consider this important problem in this paper and make the following contributions. First, a semi-Markov prediction model is proposed to predict the uncertainty of the network topology. Second, a dynamic resource table is updated by the formation transition probability which can describe the dynamic of the network topology. Third, the Q-learning method is applied to find an optimal routing in the uncertain and dynamic network topology. Numerical experiments demonstrate that the proposed method can predict the network topology more accurate and obtain an optimal routing strategy with improved transmission efficiency and reduced transmission delay.KeywordsMilitary networksSemi-MarkovTopology predictionQ-learningDynamic routing

In this paper, we investigate the problem of securing exponentially fast consensus (exponential consensus for short) for identical agents with finite-dimensional linear system dynamics over dynamic network topology. Our aim is to find the weakest possible conditions that guarantee exponentially fast consensus using a Lyapunov function consisting of a sum of terms of the same functional form. We first investigate necessary conditions, starting by examining the system (both agent and network) parameters. It is found that controllability of the linear agents is necessary for reaching consensus. Then, to work out necessary conditions incorporating the network topology, we construct a set of Laplacian matrix-valued functions. The precompactness of this set of functions is shown to be a significant generalization of existing assumptions on network topology, including the common assumption that the edge weights are bounded piecewise constant functions or continuous functions. With the aid of such a precompactness assumption and restricting the Lyapunov function to one consisting of a sum of terms of the same functional form, we prove that a joint <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$(\delta, T)$</tex-math></inline-formula> -connectivity condition on the network topology is necessary for exponential consensus. Finally, we investigate how the above two “necessities” work together to guarantee exponential consensus. To partially address this problem, we define a synchronization index to characterize the interplay between agent parameters and network topology. Based on this notion, it is shown that by designing a proper feedback matrix and under the precompactness assumption, exponential consensus can be reached globally and uniformly if the joint <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$(\delta,T)$</tex-math></inline-formula> -connectivity and controllability conditions are satisfied, and the synchronization index is not less than one.

In a 5G ultra-dense network, dynamic network topology and traffic patterns lead to excessive system overhead and complex radio resource conflicts. The cloud radio access network and the fog computing have the advantages of high computation capabilities and low transmission delays. Therefore, by taking full advantage of these two characteristics, this study proposes a novel radio resource coordination and scheduling scheme in an ultra-dense cloud-based small cell network. Interference among small cells (or remote radio heads) can be avoided by implementing centralized cooperative processing in the base band unit pool in advance. Resource sharing in coordination and transfer depend on fog computing to relieve the overloaded cloud processing platform and reduce transmission delays, thereby maximizing resource utilization and minimizing system overhead when the network topology and number of users change dynamically. The simulation shows that the proposed scheme can increase the system throughput by 20% compared with the clustering-based algorithm; it can also increase system throughput by 33% compared with the graph coloring algorithm, decrease the signaling overhead by about 50%, and improve network’s quality of service.

As the scale of the network increases, especially wireless and mobile networks comes into fashion, the problem of network dynamic topology management turns into a focus topic in the network world. When network information changes, frequent route computing and network state updates can cause computing and traffic overhead, respectively. Therefore, minimum of influence to network structure has been identified as one of the key issues in designing dynamic network routing protocols. A novel protocol, which is based on Aggregation Tree Routing Model (ATRM) as well as an effective ball-and-string algorithm, is introduced in this paper which aims to minimize the alteration of network topology and to speed up the minimum cost route computation. This routing protocol is applicable to all kinds of networks, including Internet, ad hoc and wireless sensor networks. The simulations show that our protocol not only results in significantly lower overhead, but also gives high levels of dynamic network topology management performance while keeping practical.

Mobile ad hoc networks (MANET) are collections of self-organizing mobile nodes with dynamic topologies and have no fixed infrastructure. MANET do not have centralized administration, here nodes act as both host as well as router and communicate by forwarding packets for each other in multi hop way, because of the fundamental characteristics like, the open medium, dynamic network topology, lack of centralized monitoring and management these networks are particularly vulnerable to various types of attacks. One of the routing protocol being used for wireless network is Ad hoc on demand distance vector (AODV). Black hole is one of the attack that is launched on AODV. In this attack, the attacker claims the shortest route to the destination and hinders the communication by dropping all the packets. In this paper, a new solution against the Black Hole attack is proposed. This paper demonstrates a timer based detection approach for identifying black hole node. In network layer we proposed a Timer based method to overhear the next node action. The simulation results using EXata-Cyber shows that in a dynamic network most of the malicious nodes can be detected and that results in an improved packet delivery ratio.

We investigate the use of distributed PID actions to achieve consensus and synchronization in networks of homogeneous and heterogeneous agents. We first analyze the case of distributed PID control on networks with heterogeneous nodes described by first-order linear systems. Convergence of the strategy is proved using appropriate state transformations and Lyapunov functions. Then, we propose a multiplex proportional-integral approach, for solving consensus problems in networks of heterogeneous n-dimensional node dynamics affected by constant disturbances. The proportional and integral actions are deployed on two different layers across the network, each with its own topology. Furthermore, the contribution of the network topology and node dynamics have been systematically separated giving some sufficient conditions guaranteeing convergence. Finally, an extension to networks of identical nonlinear node dynamics is presented. We provide local and global stability analysis together with a detailed performance assessment where heterogeneity among nodes and disturbances are considered. The effectiveness of the theoretical results is illustrated via its application to a representative power grid model recently presented in the literature and also for synchronization in networks of chaotic circuits.

Mobile Ad-hoc network is an autonomous system of mobile wireless nodes connected dynamically without any preexisting infrastructure. Here, since the nodes are mobile, the network topology changes rapidly and unpredictably over time. The QoS routing has challenging problems due to the network's dynamic topology. The multi hop wireless forwarding of packets, broadcasting of control traffic and the fact that, all nodes may act as routers in addition to being sources and sinks of data in ad-hoc networks produce different queuing behaviour. Hence, a scheduling algorithm to schedule the packets based on their respective priorities improves the performance of the network. Here, we present an efficient fuzzy based priority scheduler for mobile ad-hoc networks, to determine the priority of the packets. The performance of this scheduler is studied using GloMoSim and evaluated in terms of quantitative metrics such as packet delivery ratio, average end to end delay and throughput. It is found that the scheduler provides overall improvement in the performance of the system with various mobility models, when tested with different routing protocols.

Due to the high mobility and dynamic topology of the FANET network, maintaining communication links between UAVs is a challenging task. The topology of these networks is more dynamic than traditional mobile networks, which raises challenges for the routing protocol. The existing routing protocols for these networks partly fail to detect network topology changes. Few methods have recently been proposed to overcome this problem due to the rapid changes of network topology. We try to solve this problem by designing a new dynamic routing method for a group of UAVs using Hybrid SDN technology (SDN and a distributed routing protocol) with a highly dynamic topology. Comparison of the proposed method performance and two other algorithms is simulated. The simulation results show that the proposed method has better results than traditional algorithms in the package delivery ratio, average end to end delay, packet loss, throughput and normalized routing Load.

It is very difficult to find feasible QoS (Quality of service) routes in the mobile ad hoc networks (MANETs), because of the nature constrains of it, such as dynamic network topology, wireless communication link and limited process capability of nodes. In order to reduce average cost in flooding path discovery scheme of the traditional MANETs routing protocols and increase the probability of success in finding QoS feasible paths and we proposed a heuristic and distributed route discovery method named RLGAMAN that supports QoS requirement for MANETs in this study. This method integrates a distributed route discovery scheme with a reinforcement learning (RL) method that only utilizes the local information for the dynamic network environment; and the route expand scheme based on genetic algorithms (GA) method to find more new feasible paths and avoid the problem of local optimize. We investigate the performance of the RLGAMAN by simulation experiment bed in NS2. Compared with traditional method, the experiment results showed the network performance is improved obviously and RLGAMAN is efficient and effective.

The lifetime of wireless sensor networks are constrained by its limited battery capacity. Therefore, the lifetime is widely regard as a bottleneck of technique of wireless sensor network. Recently, the emerging breakthrough in wireless power transfer technique is expected to eliminate the power constraint bottleneck. In this paper, we propose an intelligent wireless charging vehicle (IWCV) strategy to resolve above problem in a dynamic and scalable approach. The IWCV strategy includes an intelligent routing strategy to traverse the sensor network topology and charging their battery to prolong their lifetime. What makes IWCV different to previous studies is that IWCV can still work even if the topology changes by re-computing the traversing route and stop time for each node in a relative short amount of time, compared with the time needed to find the shortest Hamiltoaian cycle. With the scalable and dynamic feature of IWCV, one can change their sensor network topology without down time to reconfigure the wireless charging vehicle while still maintain low energy consumption during traveling and charging in dynamic network topologies.

Cellular relay networks prove to be a cost-effective approach that offers significant performance benefits in coverage extension, cell-edge throughput enhancement and increased spectral efficiency. Radio resource management for cellular relay networks, where the network topology is highly dynamic, is particularly challenging. The highly dynamic topology may be caused by an ever increasing number of users accessing Internet and other multimedia services using mobile devices carried by pedestrians, in a train or in vehicles. This paper studies the subcarrier allocation problem in highly dynamic cellular relay networks with an objective to maximize the overall throughput. This optimization problem is formulated and solved as an expectation maximization problem. Statistical multiplexing gain is explicitly explored to further improve the channel utilization and spectral efficiency. Numerical evaluations are performed which demonstrate that the proposed scheme offers higher system throughput and improved radio resource utilization compared with existing schemes.

The multicast routing protocols used in wire network, such as distance vector multicast routing protocol(DVMRP), multicast open shortest path first(MOSPF), core based tree(CBT), do not run very well in ad hoc network because the dynamic net topology may destroy the distribution tree. Besides, distribution tree usually needs global routing structure. Which produces extra processing cost because the dynamic topology will introduce frequent exchange of routing vector or routing state between nodes. To deal with these problems multicast forwarding group routing protocol (MFGRP) which is based on route grid is designed on basis of dynamic source routing protocol (DSR). MFGRP ensures the multicast packets are sent to destination through dynamic topology network using multicast route grid.

Future Internet technologies and the deployment of mobile and nomadic services enable complex communications networks, that have a highly dynamic behavior. This naturally engenders route-discovery problems under changing conditions over these networks, but the temporal variations in the topology of dynamic networks are not effectively captured in a classical graph model. In this paper, we use evolving graphs, which help capture the dynamic characteristics of such networks, in order to compute multicast trees with minimum overall transmission time for a class of wireless mobile dynamic networks. We first show that computing different types of strongly connected components in evolving digraphs is NP-Hard, and then propose a polynomial-time algorithm to build all rooted directed Minimum Spanning Trees in strongly connected dynamic networks. These results open new avenues for the implementation of Internet spanning-tree based protocols over highly dynamic network infrastructures.

Choral singing requires the coordination of physiological subsystems within and across individuals. Previously, we suggested that the choir functions as a superordinate system that imposes boundary conditions on the dynamic features of the individual singers and found reliable differences in the network topography by analyzing within- and cross-frequency couplings (WFC and CFC, respectively). Here, we further refine our analyses to investigate hyper-frequency network (HFN) topology structures (i.e., the layout or arrangement of connections) using a graph-theoretical approach. In a sample of eleven singers and one conductor engaged in choral singing (aged between 23 and 56 years, and including five men and seven women), we calculated phase coupling (WFC and CFC) between respiratory, cardiac, and vocalizing subsystems across ten frequencies of interest. All these couplings were used for construction of HFN with nodes being a combination of frequency components and subsystems across choir participants. With regard to the network topology measures, we found that clustering coefficients (CCs) as well as local and global efficiency were highest and characteristic path lengths, correspondingly, were shortest when the choir sang a canon in parts as compared to singing it in unison. Furthermore, these metrics revealed a significant relationship to individual heart rate, as an indicator of arousal, and to an index of heart rate variability indicated by the LF/HF ratio (low and high frequency, respectively), and reflecting the balance between sympathetic and parasympathetic activity. In addition, we found that the CC and local efficiency for groups singing the same canon part were higher than for groups of singers constructed randomly post hoc, indicating stronger neighbor–neighbor connections in the former. We conclude that network topology dynamics are a crucial determinant of group behavior and may represent a potent biomarker for social interaction.

Dynamic hydrogels offer the opportunity to meet the expectations of smart materials with adaptable properties such as stimuli responsiveness, self‐healing, shear thinning, stress relaxation, dynamic viscoelasticity, energy dissipation mechanisms, time‐dependent adaptation, etc. In the past decades, reversible C═N bonds including imine, hydrazone, and oxime have received great research interest in the design of dynamic polymer networks (DPNs). Moreover, reversible C═N bonds can be well‐integrated into DPNs in combination with permanent covalent crosslinks and/or other dynamic bonds (supramolecular interactions and dynamic covalent bonds), thus outfitting the hydrogels with enhanced mechanical properties, multiresponsiveness, printability, adhesion, and various other functions. This literature review first describes how reversible C═N bonds can be introduced into hydrogels from the perspective of dynamic bonds and network topologies. The design strategies (building blocks, crosslink type combinations, network topologies) reported in the literature are then discussed, as well as the effects of dynamic crosslinking on the hydrogel properties and the potential applications.