Global Network Status Research Articles

Context-Aware Multi-Criteria Handover at the Software Defined Network Edge for Service Differentiation in Next Generation Wireless Networks

The densified deployment of heterogeneous networks coexisting with a variety of overlapping cells has emerged as a viable solution for next generation wireless networks. Despite numerous advantages, the heterogeneity and denseness also raise complicated handover management issue. Nonetheless, most existing handover methods generally depend on one or more objective attributes, and rarely consider the subjective demands of personalized users and specific applications that demand differentiated services. Through decomposing the control plane and data plane, software defined network(SDN) offers a flexible architectural paradigm to overcome these challenges. In this article, we first develop an SDN-driven handover architecture that is capable of perceiving global network status and requirements from various perspectives, including the physical layer, users, and applications. Then, a context-aware multi-criteria handover mechanism is developed in the SDN edge to provide differentiated services. Considering the numerous complicated factors, the handover decision is made based on a hierarchical fuzzy inference system to process diverse attributes and vague requirements described in natural language. Finally, we evaluate the performance of our proposed scheme through a combination of extensive simulations and real-world experiments. The results demonstrate that our solution outperforms the baseline handover schemes, more efficiently providing differentiated services with respect to throughput, bandwidth cost, and application satisfaction, and is efficient and feasible in practice.

Learning-aided client association control for high-density WLANs

As wireless local area network (WLAN) continues to become popular, there is an increasing number of clients with huge data traffic demands. Especially, some high client-density environments are emerging, such as industrial plants, stadiums, and event centers, which poses significant challenges in terms of client association control. Under such environments, conventional client-side solutions that select access points (APs) according to simple indicators such as signal strength may result in poor network performance, and although some centralized association control mechanisms are proposed, it is still difficult that a large amount of complex global network status information needs to be effectively and efficiently utilized. To meet these challenges, we investigate the online centralized association control problem that aims to improve user quality of experience (QoE), and propose a deep reinforcement learning (DRL) aided solution, called Wi-OAC, where an image-like state pattern is designed to achieve state reformulation for deep Q-network (DQN), and the double DQN and dueling DQN strategies are combined to improve convergence speed. On the basis of offline training, Wi-OAC can determine the proper AP-client associations for the arriving clients. Both simulation experiments and real-world experiments have been conducted to validate the effectiveness of Wi-OAC. In real-world experiments, we build a Wi-OAC testbed including 3 APs and 54 clients in less than 10.5 m2 area, and the results show that Wi-OAC can significantly improve the performance on the client throughput, AP load balancing and user QoE.

Conceptual Framework for Secure Cluster Management In Software Networks

Software Defined Networks (SDN) is a new concept of network architecture that provides the separation of control plane (controller) and data plane (switches) in network devices. Hidden Markov Model (HMM) scheme is proposed for cluster management. The utilization of the bandwidth is an issue because of the extensibility of the control plane. The Control plane in SDN focuses on a centralized solution, where a single control entity has an overall view of the network. To meet the administration, the board necessities of large-scale network situations, the controls plane is regularly completed in the sort of distributed controller clusters, Cluster management technology monitors all sort of events and should keep up a reliable global network status, which usually leads to big data in SDNs. Cluster management technology monitors all types of events and must maintain a consistent global network status, which usually leads to big data in SDNs. Simultaneously, the cluster security is an open issue because of the programmable and dynamic features of SDNs.

Research on the evolution of global internet network interconnection relationship in 21 years

The global Internet is composed of tens of thousands of autonomous system networks that are interconnected through a border gateway protocol. The analysis of changes in the interconnected relationships of the global Internet network is essential for studying the evolutionary trend of the global Internet. In addition, this analysis can also contribute toward the research on China's Internet development gaps. This article draws on the global Internet network status map for 21 years, starting from 1998 to 2019, based on inter-domain routing data sets of international third parties and China Academy of Information and Communications Technology. Moreover, the article also conducts a big data analysis on the relationship between global Internet network changes. The research results show that the global Internet network interconnection has increased, by nearly 60 times in the past 21 years. Peer-to-peer interconnection has gradually surpassed transit interconnection as the main mode of global interconnection. Furthermore, large Internet companies are playing an increasingly important role in global interconnection. Simultaneously, the results indicate the gradual movement of China's Internet base toward the global core and the continuous improvements of the global network's status.

Development of algorithms of self-organizing network for reliable data exchange between autonomous robots

Factors affecting the reliability of data transmission in networks with nodes with periodic availability were considered. The principles of data transfer between robots are described; the need for global connectivity of communications within an autonomous system is shown, since the non-availability of information on the intentions of other robots reduces the effectiveness of the robotics system as a whole and affects the fault tolerance of a team of independent actors performing distributed activities. It is shown that the existing solutions to the problem of data exchange based on general-purpose IP networks have drawbacks; therefore, as the basis for organizing autonomous robot networks, we used developments in the domain of topological models of communication systems allowing us to build self-organizing computer networks. The requirements for the designed network for reliable message transfer between autonomous robots are listed, the option of organizing reliable message delivery using overlay networks, which expand the functionality of underlying networks, is selected. An overview of existing popular controlled and non-controlled overlay networks is given; their applicability for communication within a team of autonomous robots is evaluated. The features and specifics of data transfer in a team of autonomous robots are listed. The algorithms and architecture of the overlay self-organizing network were described by means of generally accepted methods of constructing decentralized networks with zero configurations. As a result of the work, general principles of operation of the designed network were proposed, the message structure for the delivery algorithm was described; two independent data streams were created, i.e. service and payload; an algorithm for sending messages between network nodes and an algorithm for collecting and synchronizing the global network status were developed. In order to increase the dependability and fault tolerance of the network, it is proposed to store the global network status at each node. The principles of operation of a distributed storage are described. For the purpose of notification on changes in the global status of the network, it is proposed to use an additional data stream for intra-network service messages. A flood routing algorithm was developed to reduce delays and speed up the synchronization of the global status of a network and consistency maintenance. It is proposed to provide network connectivity using the HELLO protocol to establish and maintain adjacency relations between network nodes. The paper provides examples of adding and removing network nodes, examines possible scalability problems of the developed overlay network and methods for solving them. It confirms the criteria and indicators for achieving the effect of self-organization of nodes in the network. The designed network is compared with existing alternatives. For the developed algorithms, examples of latency estimates in message delivery are given. The theoretical limitations of the overlay network in the presence of intentional and unintentional defects are indicated; an example of restoring the network after a failure is set forth.

Big Data Analysis-Based Secure Cluster Management for Optimized Control Plane in Software-Defined Networks

In software-defined networks (SDNs), the abstracted control plane is its symbolic characteristic, whose core component is the software-based controller. The control plane is logically centralized, but the controllers can be physically distributed and composed of multiple nodes. To meet the service management requirements of large-scale network scenarios, the control plane is usually implemented in the form of distributed controller clusters. Cluster management technology monitors all types of events and must maintain a consistent global network status, which usually leads to big data in SDNs. Simultaneously, the cluster security is an open issue because of the programmable and dynamic features of SDNs. To address the above challenges, this paper proposes a big data analysis-based secure cluster management architecture for the optimized control plane. A security authentication scheme is proposed for cluster management. Moreover, we propose an ant colony optimization approach that enables big data analysis scheme and the implementation system that optimizes the control plane. Simulations and comparisons show the feasibility and efficiency of the proposed scheme. The proposed scheme is significant in improving the security and efficiency SDN control plane.

Simple and efficient self-healing strategy for damaged complex networks.

The process of destroying a complex network through node removal has been the subject of extensive interest and research. Node loss typically leaves the network disintegrated into many small and isolated clusters. Here we show that these clusters typically remain close to each other and we suggest a simple algorithm that is able to reverse the inflicted damage by restoring the network's functionality. After damage, each node decides independently whether to create a new link depending on the fraction of neighbors it has lost. In addition to relying only on local information, where nodes do not need knowledge of the global network status, we impose the additional constraint that new links should be as short as possible (i.e., that the new edge completes a shortest possible new cycle). We demonstrate that this self-healing method operates very efficiently, both in model and real networks. For example, after removing the most connected airports in the USA, the self-healing algorithm rejoined almost 90% of the surviving airports.

Synaptic scaling generically stabilizes circuit connectivity

Neural systems regulate synaptic plasticity avoiding overly strong growth or shrinkage of the connections, thereby keeping the circuit architecture operational. Accordingly, several experimental studies have shown that synaptic weights increase only in direct relation to their current value, resulting in reduced growth for stronger synapses [1]. It is, however, difficult to extract from these studies unequivocal evidence about the underlying biophysical mechanisms that control weight growth. The theoretical neurosciences have addressed this problem by exploring mechanisms for synaptic weight change that contain limiting factors to regulate growth [2]. The effectiveness of these mechanisms is difficult to justify from a biophysical perspective, in particular those that require knowledge of global network status (e.g. knowledge of the ‘sum of all weights’) for normalization. Also spike-timing-dependent plasticity [3] cannot guaranty stability because various types of plasticity exist across different neurons and even at the same neuron, depending on the location of the synapses [1]. Therefore, it remains an open question how neural circuits simultaneously stabilize their many synapses and ensure diversity in the presence of a variety of distinct plasticity mechanisms. In 1998, a series of studies initiated by Turrigiano augmented this discussion by demonstrating that network activity is homeostatically regulated, suggesting that weights ω are regulated by an activity-dependent difference term [4,5]. Accordingly, synaptic scaling compares output activity v against a desired target activity vT of each individual neuron [5]. Most straightforwardly, such a local weight change is defined by dω/dt = γH(νT – ν) [6], where the long characteristic time scale (hours up to days) of synaptic scaling is determined by a small factor γ << 1. Synaptic scaling operates in parallel to conventional plasticity and acts simultaneously on different synapses. Here we suggest that synaptic scaling is combined with different types of plasticity mechanisms in the same circuit or even at the same neuron and regulates synaptic diversity across the circuit. We demonstrate that it robustly yields stable and diverse weight distributions which moreover are independent of the individual plasticity mechanism. As scaling co-acts with plasticity, such a combined mechanism is mathematically characterized by a weight change dω/dt = μG + γH. Here μ defines the rate of change of conventional synaptic plasticity, γ <<μ << 1, and G and H describe the specific types of plasticity and scaling, respectively [7]. For example, G is different for plain Hebbian plasticity than for STDP. As we show, combining any type of conventional plasticity G with nonlinear weight-dependent scaling H naturally yields global synaptic stabilization across the circuit regardless of the specific form of the plasticity G and also largely independent of the intrinsic neuron dynamics. Our study demonstrates that synapses are stabilized strictly in an input-determined way thereby capturing characteristic features of the inputs to the network. As an important result, we show that such systems are capable of representing a given input pattern via stably changed weights along several stages of signal propagation. This holds even in circuits containing a substantial number of random recurrent connections but no particular additional architecture.

Collapsar: A VM-based honeyfarm and reverse honeyfarm architecture for network attack capture and detention

The honeypot has emerged as an effective tool to provide insights into new attacks and exploitation trends. However, a single honeypot or multiple independently operated honeypots only provide limited local views of network attacks. Coordinated deployment of honeypots in different network domains not only provides broader views, but also create opportunities of early network anomaly detection, attack correlation, and global network status inference. Unfortunately, coordinated honeypot operation require close collaboration and uniform security expertise across participating network domains. The conflict between distributed presence and uniform management poses a major challenge in honeypot deployment and operation. To address this challenge, we present Collapsar, a virtual machine-based architecture for network attack capture and detention. A Collapsar center hosts and manages a large number of high-interaction virtual honeypots in a local dedicated network. To attackers, these honeypots appear as real systems in their respective production networks. Decentralized logical presence of honeypots provides a wide diverse view of network attacks, while the centralized operation enables dedicated administration and convenient event correlation, eliminating the need for honeypot expertise in every production network domain. Collapsar realizes the traditional honeyfarm vision as well as our new reverse honeyfarm vision, where honeypots act as vulnerable clients exploited by real-world malicious servers. We present the design, implementation, and evaluation of a Collapsar prototype. Our experiments with a number of real-world attacks demonstrate the effectiveness and practicality of Collapsar.

A Technique for Adaptive Routing in Networks

A two-level adaptive routing scheme for packet-switched computer communication networks is proposed and investigated. The first level is quasi-static and based on the global network status. The second level is dynamic with decisions being made at each node in an attempt to obtain the savings in average delay predicted by a multiserver model of the node. Simulations confirm the predicted improvement.