Cognitive network

About: Cognitive network is a research topic. Over the lifetime, 4213 publications have been published within this topic receiving 107093 citations.

Cognitive passive estimation of available bandwidth (cPEAB) in overlapped IEEE 802.11 WiFi WLANs

Abstract: Correct estimation of the available bandwidth in overlapped WiFi WLANs environments is one of the essential functions for efficient network resource management and seamless mobile service provisioning of QoS-guaranteed realtime multimedia applications in future Internet. In this paper, we propose a cognitive passive estimation of the available bandwidth (cPEAB) by correct measurements of i) the proportion of waiting and back-off delay, ii) packet collision probability, iii) acknowledgement delay, and iv) channel idle time compared to measurement period. For more accurate estimation of the available bandwidth, the information of the hidden nodes and exposed nodes are provided by the cognitive network management system. Also, the proposed scheme is using passive measurements, instead of active probe packet exchange which directly affects the available bandwidth of other mobile nodes. The proposed cPEAB scheme has been implemented on Multiband Atheros Driver for WiFi (MadWiFi), and the performance has been analyzed and compared with existing schemes, such as active bandwidth measurements with probes, adaptive admission control protocol (AAC), available bandwidth estimation (ABE), and improved available bandwidth estimation (IAB). From the experimental measurements on real WiFi environment, we found that the proposed cPEAB provides the most accurate estimation of available bandwidth on the overlapped WiFi WLAN environment where the hidden/exposed nodes are dynamically affecting the available bandwidth.

Cognitive Network Inference through Bayesian Network Analysis

Abstract: Cognitive networking deals with applying cognition to the entire network protocol stack for achieving stack-wide as well as network-wide performance goals, unlike cognitive radios that apply cognition only at the physical layer. Designing a cognitive network is challenging since learning the relationship between network protocol parameters in an automated fashion is very complex. We propose to use Bayesian Network (BN) models for creating a representation of the dependence relationships among network protocol parameters. BN is a unique tool for modeling the network protocol stack as it not only learns the probabilistic dependence of network protocol parameters but also provides an opportunity to tune some of the cognitive network parameters to achieve desired performance. To the best of our knowledge, this is the first work to explore the use of BNs for cognitive networks. Creating a BN model for network parameters involves the following steps: sampling the network protocol parameters (Observe), learning the structure of the BN and its parameters from the data (Learn), using a Bayesian Network inference engine (Plan and Decide) to make decisions, and finally effecting the decisions (Act). We have proved the feasibility of achieving a BN-based cognitive network system using the ns-3 simulation platform. From the early results obtained from our cognitive network approach, we provide interesting insights on predicting the network behavior, including the performance of the TCP throughput inference engine based on other observed parameters.

A Learning Framework for Cognitive Interference Networks with Partial and Noisy Observations

Abstract: An algorithm for the optimization of secondary user's transmission strategies in cognitive networks with imperfect network state observations is proposed. The secondary user minimizes the time average of a cost function while generating a bounded performance loss to the primary users' network. The state of the primary users' network, defined as a collection of variables describing features of the network (e.g., buffer state, ARQ state) evolves over time according to a homogeneous Markov process. The statistics of the Markov process is dependent on the strategy of the secondary user and, thus, the instantaneous idleness/transmission action of the secondary user has a long-term impact on the temporal evolution of the network. The Markov process generates a sequence of states in the state space of the network that projects onto a sequence of observations in the observation space, that is, the collection of all the observations of the secondary user. Based on the sequence of observations, the proposed algorithm iteratively optimizes the strategy of the secondary users with no a priori knowledge of the statistics of the Markov process and of the state-observation probability map.

QoS multicast routing protocol oriented to cognitive network using competitive coevolutionary algorithm

Abstract: The human intervention in the network management and maintenance should be reduced to alleviate the ever-increasing spatial and temporal complexity. By mimicking the cognitive behaviors of human being, the cognitive network improves the scalability, self-adaptation, self-organization, and self-protection in the network. To implement the cognitive network, the cognitive behaviors for the network nodes need to be carefully designed. Quality of service (QoS) multicast is an important network problem. Therefore, it is appealing to develop an effective QoS multicast routing protocol oriented to cognitive network. In this paper, we design the cognitive behaviors summarized in the cognitive science for the network nodes. Based on the cognitive behaviors, we propose a QoS multicast routing protocol oriented to cognitive network, named as CogMRT. It is a distributed protocol where each node only maintains local information. The routing search is in a hop by hop way. Inspired by the small-world phenomenon, the cognitive behaviors help to accumulate the experiential route information. Since the QoS multicast routing is a typical combinatorial optimization problem and it is proved to be NP-Complete, we have applied the competitive coevolutionary algorithm (CCA) for the multicast tree construction. The CCA adopts novel encoding method and genetic operations which leverage the characteristics of the problem. We implement and evaluate CogMRT and other two promising alternative protocols in NS2 platform. The results show that CogMRT has remarkable advantages over the counterpart traditional protocols by exploiting the cognitive favors.

Demonstrating cognitive packet network resilience to worm attacks

Abstract: The need for network stability and reliability has led to the growth of autonomic networks that can provide more stable and more reliable communications via on-line measurement, learning and adaptation. A promising architecture is the Cognitive Packet Network (CPN) that rapidly adapts to varying network conditions and user requirements using QoS driven reinforcement learning algorithms that drive the routing control. Contrary to conventional mechanisms, the users rather than the nodes, control the routing by specifying their desired QoS requirements (QoS Goals), such as Minimum Delay, Maximum Bandwidth, Minimum Cost, etc., and the network then routes each user's traffic individually based on their specific needs and on a "glocal" view. In CPN the user has the ability to explore the network for its own needs, and evaluate its own impact on the network as a whole and vice-versa, and then take appropriate decisions. CPN routing has been evaluated extensively under normal operating conditions and has proven to be very adaptive to network changes such as congestion. Here we show how CPN can respond and survive to catastrophic node failures caused by the spread of network worms. This survival is based on two complementary approaches that are run concurrently: one the one hand, each user attempts to concurrently and adaptively avoid paths which are infected, and secondly patching algorithms are continuously run to repair the network. Experiments show that this approach assures the stability of network communications throughout the course of an attack.