Cognitive Packet Network Research Articles

Self-Administered Information Sharing Framework Using Bioinspired Mechanisms

The promising potential of distributed and interconnected lightweight devices that can jointly generate superior information-collecting and problem-solving abilities has long fostered various significant and ubiquitous techniques, from wireless sensor networks (WSNs) to Internet of Things (IoT). Although related applications have been widely used in different domains in attempting to collect and harness the ever-growing information flows, one major issue that impedes the further advancement of WSNs or IoT-based applications is the restricted battery power. Previous research mainly focuses on investigating novel protocols to save energy by reducing data traffic with the aid of optimal or heuristic algorithms. However, data packet behaviours and significant parameters involved are mostly preconfigured in a supervised-learning fashion rather than using an unsupervised learning paradigm and therefore may not adapt to uncertain or fast-changing environments. Hence, this paper concentrates on optimising the behaviours of data packets and significant parameters in a widely tested routing protocol, namely, Cognitive Packet Network (CPN), with the aid of several bio-inspired algorithms to increase the efficiency of energy usage and information acquisition. Two novel packet behaviours are introduced, and an on-line parameter calibration scheme is proposed to realise packet time-to-live (TTL) adjustment and rate adaptation. The simulation results show that the introduction of the bioinspired algorithms can improve the efficiency of information sharing and reduce the energy consumption.

Deep Learning Clusters in the Cognitive Packet Network

The Cognitive Packet Network (CPN) bases its routing decisions and flow control on the Random Neural Network (RNN) Reinforcement Learning algorithm; this paper proposes the addition of a Deep Learning (DL) Cluster management structure to the CPN for Quality of Service metrics (Delay Loss and Bandwidth), Cyber Security keys (User, Packet and Node) and Management decisions (QoS, Cyber and CEO). The RNN already models how neurons transmit information using positive and negative impulsive signals whereas the proposed additional Deep Learning structure emulates the way the brain learns and takes decisions; this paper presents a brain model as the combination of both learning algorithms, RNN and DL. The proposed model has been simulated under different network sizes and scenarios and it has been validated against the CPN itself without DL clusters. The simulation results are promising; the presented CPN with DL clusters as a mechanism to transmit, learn and make packet routing decisions is a step closer to emulate the way the brain transmits information, learns the environment and takes decisions.

Reliable Communication in Transmission Grids based on Nondisjoint Path Aggregation Using Software-Defined Networking

In electrical transmission grids, the redundant communication paths nondisjointly overlapping at links can be established between certain substations and the control center to guarantee reliable packet delivery under link failures. However, the generation of nondisjoint paths with multiplicative and concave constraints is with the NP-complete complexity and the failovers can lead to out-of-order packets. This paper presents an OpenFlow-based nondisjoint path aggregation mechanism to heuristically compute the constrained nondisjoint paths in a centralized fashion and reorganize the out-of-order packets at edge switches. The solution is evaluated through simulations of the IEEE 30-bus network scenario under 2% link failure rate and the result confirms its effectiveness: the packet delivery success rate is significantly improved in comparison with the current nondisjoint and disjoint path algorithms. TCP throughput is improved by 121.62% with the packet reordering. Also, the memory usage for the packet reordering buffer is reduced by 76.563% compared with the distributed cognitive packet network.

Deep Learning Cluster Structures for Management Decisions: The Digital CEO.

This paper presents a Deep Learning (DL) Cluster Structure for Management Decisions that emulates the way the brain learns and makes choices by combining different learning algorithms. The proposed model is based on the Random Neural Network (RNN) Reinforcement Learning for fast local decisions and Deep Learning for long-term memory. The Deep Learning Cluster Structure has been applied in the Cognitive Packet Network (CPN) for routing decisions based on Quality of Service (QoS) metrics (Delay, Loss and Bandwidth) and Cyber Security keys (User, Packet and Node) which includes a layer of DL management clusters (QoS, Cyber and CEO) that take the final routing decision based on the inputs from the DL QoS clusters and RNN Reinforcement Learning algorithm. The model has been validated under different network sizes and scenarios. The simulation results are promising; the presented DL Cluster management structure as a mechanism to transmit, learn and make packet routing decisions is a step closer to emulate the way the brain transmits information, learns the environment and takes decisions.

A generalized reinforcement learning scheme for random neural networks

We propose a reinforcement learning scheme for random neural networks (RNN) that update network weights based on the relative reward obtained by past actions. This new learning scheme achieves improved performance in random environments under certain conditions, in particular, when the number of actions is small. We also explore hybrid learning structures, where a RNN functions as a meta decision unit that learns how to best delegate the action decision to a second layer of decision units. An extensive simulation study demonstrates the performance of these learning methods applied to minimizing response times in a distributed task assignment scenario. Results are compared to the cognitive packet networks’ reinforcement learning scheme, a reward-only variation, and several non-learning methods. The study reveals that no single method can produce the best performance results in all cases. However, both the generalized reinforcement learning scheme and the application of meta decision units can help to achieve improved performance in specific cases.

THE RANDOM NEURAL NETWORK FOR COGNITIVE TRAFFIC ROUTING AND TASK ALLOCATION IN NETWORKS AND THE CLOUD

G-Network queueing network models, and in particular the random neural network (RNN), are useful tools for decision making in complex systems, due to their ability to learn from measurements in real time, and in turn provide real-time decisions regarding resource and task allocation. In particular, the RNN has led to the design of the cognitive packet network (CPN) decision tool for the routing of packets in the Internet, and for task allocation in the Cloud. Thus in this paper, we present recent research on how to dynamically create the means for quality of service (QoS) to end users of the Internet and in the Cloud. The approach is based on adapting the decisions so as to benefit users as the conditions in the Internet and in Cloud servers vary due to changing traffic and workload. We present an overview of the algorithms that were designed based on the RNN, and also detail the experimental results that were obtained in three areas: (i) traffic routing for real-time applications, which have strict QoS constraints; (ii) routing approaches, which operate at the overlay level without affecting the Internet infrastructure; and (iii) the routing of tasks across servers in the Cloud through the Internet.

EROL GELENBE: A CAREER IN MULTI-DISCIPLINARY PROBABILITY MODELS

We focus on Erol Gelenbe's scientific and technical contributions to probability models in the computer and information sciences, but limit our survey to the last fifteen years. We start with a brief overview of his work as a single author, as well as his work in collaboration with over 200 co-authors. We discuss some of his recent and innovative work regarding a new probability model that represents Intermittent Energy Sources for Computing and Communications, introducingEnergy Packet Networkswhich are a probabilistic representation of the flow, storage and consumption of electrical energy at the microscopic level (in electronic chips), and at the macroscopic level (e.g. in buildings or data centers) and for its routing and dynamic usage by consuming units (such as computer elements, chips or machines). We next discuss his work on designing computer and communication systems that parsimoniously use energy in order to achieve a satisfactory level of quality of service (QoS). Trade-offs between system QoS and energy consumption are also considered. Then we turn to Prof. Gelenbe's pioneering work on Autonomic Communications and the design and implementation of CPN, the Cognitive Packet Network, and we also briefly review his spiking random neural network that was used in CPN. This is followed by a brief review of work that he conducted since 1999 on human evacuation from dangerous or catastrophic environments, and the design of technology driven Emergency Management Systems. His research since the late 2000s on Gene Regulatory Networks is then covered together with its application to the detecting possible disease from microarray data. Finally, we briefly discuss some novel analytical models that he developed in this period with publications appearing in journals of physics and applied mathematics.

Big Data for Autonomic Intercontinental Overlays

This paper uses big data and machine learning for the real-time management of Internet scale quality-of-service (QoS) route optimisation with an overlay network. Based on the collection of data sampled every 2 min over a large number of source-destinations pairs, we show that intercontinental Internet protocol (IP) paths are far from optimal with respect to QoS metrics such as end-to-end round-trip delay. We, therefore, develop a machine learning-based scheme that exploits large scale data collected from communicating node pairs in a multihop overlay network that uses IP between the overlay nodes, and selects paths that provide substantially better QoS than IP. Inspired from cognitive packet network protocol, it uses random neural networks with reinforcement learning based on the massive data that is collected, to select intermediate overlay hops. The routing scheme is illustrated on a 20-node intercontinental overlay network that collects some 2 × 10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">6</sup> measurements per week, and makes scalable distributed routing decisions. Experimental results show that this approach improves QoS significantly and efficiently.

Managing Crowds in Hazards With Dynamic Grouping

Emergency navigation algorithms for evacuees in confined spaces typically treat all evacuees in a homogeneous manner, using a common metric to select the best exit paths. In this paper, we present a quality of service (QoS) driven routing algorithm to cater to the needs of different types of evacuees based on age, mobility, and level of resistance to fatigue and hazard. Spatial information regarding the location and the spread of hazards is also integrated into the routing metrics to avoid situations where evacuees may be directed toward hazardous zones. Furthermore, rather than persisting with a single decision algorithm during an entire evacuation process, we suggest that evacuees may adapt their course of action with regard to their ongoing physical condition and environment. A widely tested routing protocol known as the cognitive packet network with random neural networks and reinforcement learning are employed to collect information and provide advice to evacuees, and is beneficial in emergency navigation owing to its low computational complexity and its ability to handle multiple QoS metrics in its search for safe exit paths. The simulation results indicate that the proposed algorithm, which is sensitive to the needs of evacuees, produces better results than the use of a single metric. Simulations also show that the use of dynamic grouping to adjust the evacuees' category, and routing algorithms that have regard for their on-going health conditions and mobility, can achieve higher survival rates.

Emergency navigation without an infrastructure.

Emergency navigation systems for buildings and other built environments, such as sport arenas or shopping centres, typically rely on simple sensor networks to detect emergencies and, then, provide automatic signs to direct the evacuees. The major drawbacks of such static wireless sensor network (WSN)-based emergency navigation systems are the very limited computing capacity, which makes adaptivity very difficult, and the restricted battery power, due to the low cost of sensor nodes for unattended operation. If static wireless sensor networks and cloud-computing can be integrated, then intensive computations that are needed to determine optimal evacuation routes in the presence of time-varying hazards can be offloaded to the cloud, but the disadvantages of limited battery life-time at the client side, as well as the high likelihood of system malfunction during an emergency still remain. By making use of the powerful sensing ability of smart phones, which are increasingly ubiquitous, this paper presents a cloud-enabled indoor emergency navigation framework to direct evacuees in a coordinated fashion and to improve the reliability and resilience for both communication and localization. By combining social potential fields (SPF) and a cognitive packet network (CPN)-based algorithm, evacuees are guided to exits in dynamic loose clusters. Rather than relying on a conventional telecommunications infrastructure, we suggest an ad hoc cognitive packet network (AHCPN)-based protocol to adaptively search optimal communication routes between portable devices and the network egress nodes that provide access to cloud servers, in a manner that spares the remaining battery power of smart phones and minimizes the time latency. Experimental results through detailed simulations indicate that smart human motion and smart network management can increase the survival rate of evacuees and reduce the number of drained smart phones in an evacuation process.

Cognitive Packet Network for Bilateral Asymmetric Connections

Network testbed experimentation is useful to evaluate new protocols, since it offers realism and repeatability under controllable conditions. Thus, in this paper, we make use of a software network platform, the cognitive packet network (CPN), to offer best-effort quality of service (QoS) to end users and to develop a new bilateral QoS differentiation between pairs of communicating nodes. In the proposed approach, each CPN edge or user node is a source and a destination at the same time, managing uplink user-originated traffic and downlink traffic sent back in response to the uplink. The bilateral communication is implemented with four distinct QoS objectives that can be met between sender nodes (original source or destination). Traffic volume asymmetry between the received and the sent data is used to trigger changes in QoS. The lower traffic rate requires short-delay QoS, whereas the higher traffic rate requires loss minimization. The effectiveness of the approach is evaluated by several measurements.

Routing Diverse Evacuees with the Cognitive Packet Network Algorithm

Regarding mobility, health conditions and personal preferences, evacuees can be categorized into different classes in realistic environments. Previous emergency navigation algorithms that direct evacuees with a single decision rule cannot fulfil civilians’ distinct service requirements and increase the likelihood of inducing destructive crowd behaviours, such as clogging, pushing and trampling, due to diverse mobility. This paper explores a distributed emergency navigation algorithm that employs the cognitive packet network concept to tailor different quality of service needs to different categories of evacuees. In addition, a congestion-aware algorithm is presented to predict the future congestion degree of a path with respect to the observed population density, arrival rate and service rate of each route segment. Experiments are implemented in a simulated environment populated with autonomous agents. Results show that our algorithm can increase the number of survivors while providing improved quality of service.

Strengthening the security of cognitive packet networks

Route selection in cognitive packet networks CPNs occurs continuously for active flows and is driven by the users' choice of a quality of service QoS goal. Because routing occurs concurrently to packet forwarding, CPN flows are able to better deal with unexpected variations in network status, while still achieving the desired QoS. Random neural networks RNNs play a key role in CPN routing and are responsible to the next-hop decision making of CPN packets. By using reinforcement learning, RNNs' weights are continuously updated based on expected QoS goals and information that is collected by packets as they travel on the network experiencing the current network conditions. CPN's QoS performance had been extensively investigated for a variety of operating conditions. Its dynamic and self-adaptive properties make them suitable for withstanding availability attacks, such as those caused by worm propagation and denial-of-service attacks. However, security weaknesses related to confidentiality and integrity attacks have not been previously examined. Here, we look at related network security threats and propose mechanisms that could enhance the resilience of CPN to confidentiality, integrity and availability attacks.

Multi-path routing based on load-balance for cognitive packet networks

Quality of service (QoS) routing algorithms have been hardly discussed in the scientific community, most previous work on QoS routing concentrates on the performance of the single route. Cognitive packet network (CPN) has been designed for providing QoS routing. In this paper, to balance the loads among networks, we present a multi-path routing algorithm based on load-balance (MPRLB), which is carried out in two steps. The algorithm with low computational complexity is firstly applied to establish multi path routing for each source and destination node pairs (SD-pair) nodes in the network. Then, we propose the hopfield neural network algorithm, which is applied to improve the efficiency of the flow deviation method for fast flow allocation among the links of the network based on load balance. Extensive simulation results demonstrate that the proposed scheme significantly improves the performance compared with the existing scheme that ignores load balancing.

Performance evaluation of the Cognitive Packet Network in the presence of network worms

Reliable networks that provide good service quality are expected to become more crucial in every aspect of communication, especially as the information transferred between network users gets more complex and demanding and as malicious users try to deliberately degrade or altogether deny legitimate network service. The Cognitive Packet Network (CPN) routing protocol provides Quality of Service (QoS) driven routing and performs self-improvement in a distributed manner, by learning from the experience of special packets, which gather on-line QoS measurements and discover new routes. Although CPN is generally very resilient to network changes, it may suffer worse performance during node failures caused by network threats, such as network worms. Here we evaluate the performance of CPN in such crises and compare it with the Open Shortest Path First (OSPF) routing protocol, an industry standard and widely used in Internet Protocol networks. We also improve it by introducing a failure detection element that reduces packet loss and delay during failures. Our experiments were performed in a real networking testbed.

Energy-aware routing in the Cognitive Packet Network

An energy aware routing protocol (EARP) is proposed to minimise a performance metric that combines the total consumed power in the network and the QoS that is specified for the flows. The algorithm uses source routing based on the functionalities provided by the Cognitive Packet Network (CPN), running autonomously at each input node to the network based on smart packets which gather relevant information throughout the network using reinforcement learning at each of the intermediate nodes. Measurements on an experimental test-bed that uses EARP are presented and they indicate that it offers a reduction in power consumption, as compared to a purely QoS driven approach, and also respects the requested QoS level.

Cognitive and self-selective routing for sensor networks

New approaches to Quality-of-Service (QoS) routing in wireless sensor networks which use different forms of learning are the subject of this paper. The Cognitive Packet Network (CPN) algorithm uses smart packets for path discovery, together with reinforcement learning and neural networks, while Self-Selective Routing (SSR) is based on the “Ant Colony” paradigm which emulates the pheromone-based technique which ants use to mark paths and communicate information about paths between different insects of the same colony (Koenig et al. in Ann Math Artif Intell 31(1–4): 41–76, 2001). In this paper, we present first experimental results on a network test-bed to evaluate CPN’s ability to discover paths having the shortest delay, or shortest length. Then, we present small test-bed experiments and large-scale network simulations to evaluate the effectiveness of the SSR algorithm. Finally, the two approaches are compared with respect to their ability to adapt as network conditions change over time.

The Cognitive Packet Network: A Survey

Current and future multimedia networks require connections under specific quality of service (QoS) constraints which can no longer be provided by the best-effort Internet. Therefore, ‘smarter’ networks have been proposed in order to cover this need. The cognitive packet network (CPN) is a routing protocol that provides QoS-driven routing and performs self-improvement in a distributed manner, by learning from the experience of special packets, which gather on-line QoS measurements and discover new routes. The CPN was first introduced in 1999 and has been used in several applications since then. Here we provide a comprehensive survey of its variations, applications and experimental performance evaluations.

Reduced complexity algorithms for cognitive packet network routers

The cognitive packet network (CPN) routing protocol provides a framework for real-time quality of service decision making within packet networks. This allows the paths taken by packets to autonomously adapt to changing conditions in order to maintain and improve on the quality of service provided by current routing algorithms. Software implementations of the protocol use the random neural network with reinforcement learning. This algorithm is unsuitable for implementation in dedicated hardware or devices with low computational abilities due to its complexity. We present a series of alternative algorithms for use in CPN, and compare their complexity and performance with respect to software and hardware implementation. Through experimentation we demonstrate that it is possible to match the performance of the random neural network with the simpler alternative algorithms. We also propose an architecture for an FPGA based hardware CPN router, and describe our implementation.

Oscillations in self-aware networks

Adaptive routing is once again of interest owing to the possibility to couple online probing in networks with real-time dynamic and distributed control of paths and flows. Wireless networks, with their rapidly changing network conditions also create a need to revisit this issue. This paper uses measurements in a wired adaptive network test bed, the cognitive packet network (CPN), to investigate the pros and cons of adaptive routing. CPN routes packet flows through a store and forward network according to their quality of service (QoS) needs through an online distributed reinforcement learning mechanism. This paper investigates routing oscillations that occur due to the interaction of multiple flows and studies their effect on QoS in the context of CPN. Our results indicate that routing oscillations can be easily controlled by randomizing the route switching, and that from an overall QoS viewpoint increased switching can also lead to improved performance.