Peixiang Liu

QoS and routing in the cognitive packet network

We present experimental results on an autonomic network test-bed, the cognitive packet network (CPN), designed for research in adaptive quality-of-service (QoS) management. CPN is fully compatible at its edges with the Internet Protocol, while internally it offers dynamic routing based on on-line sensing and monitoring. CPN can implement distributed adaptive shortest-path routing, and we compare it with minimum-delay based routing and a composite approach.

CPN and QoS Driven Smart Routing in Wired and Wireless Networks

There exists an increasing need for dynamic mechanisms that take into account quality of service provisions in the establishment of routes in communication networks. Recently, we introduced a quality of service (QoS) driven routing algorithm called “Cognitive Packet Network” (CPN), which dynamically selects paths through a store-and-forward packet network so as to offer best effort QoS to an end-to-end traffic. This paper discusses a number of extensions to the algorithm: the incorporation of selective broadcasts to support the operation of an ad hoc network, the use of delay, loss, and energy information as metrics for routing, and the use of genetic algorithms to generate and maintain paths from previously discovered information by matching their “fitness” with respect to the desired QoS. We discuss implementation considerations as well as simulation and experimental results on a network testbed.

Searching for low latency routes in CPN with reduced packet overhead

Most applications consider network latency as an important metric for their operation. Latency plays a particular role in time-sensitive applications, such as, data transfers or interactive sessions. Smart packets in cognitive packet networks, can learn to find low-latency paths by explicitly expressing delay in their routing goal functions. However, to maintain the quality of paths, packets need to continuously monitor the round-trip delay that paths produce, to allow the algorithm learn any change. The acquisition of network status requires space in packets and lengthens their transmission time. This paper proposes an alternative composite goal consisting of path length and buffer occupancy of nodes that requires less storage space in packets, while offering a similar performance to a delay based goal. Measurements in a network testbed and simulation studies illustrate the problem and solution addressed in this study.

Random neural networks for the adaptive control of packet networks

The Random Neural Network (RNN) has been used in a wide variety of applications, including image compression, texture generation, pattern recognition, and so on. Our work focuses on the use of the RNN as a routing decision maker which uses Reinforcement Learning (RL) techniques to explore a search space (i.e. the set of all possible routes) to find the optimal route in terms of the Quality of Service metrics that are most important to the underlying traffic. We have termed this algorithm as the Cognitive Packet Network (CPN), and have shown in previous works its application to a variety of network domains. In this paper, we present a set of experiments which demonstrate how CPN performs in a realistic environment compared to a priori-computed optimal routes. We show that RNN with RL can autonomously learn the best route in the network simply through exploration in a very short time-frame. We also demonstrate the quickness with which our algorithm is able to adapt to a disruption along its current route, switching to the new optimal route in the network. These results serve as strong evidence for the benefits of the RNN Reinforcement Learning algorithm which we employ.

The Random Neural Network and its learning process in Cognitive Packet Networks

The Random Neural Network (RNN) is a recurrent neural network in which neurons interact with each other by exchanging excitatory and inhibitory spiking signals. The stochastic excitatory and inhibitory interactions in the network make the RNN an excellent modeling tool for various interacting entities. It has been applied in a number of applications such as optimization, image processing, communication systems, simulation pattern recognition and classification. In this paper, we briefly describe the RNN model and some learning algorithms for RNN. We discuss how the RNN with reinforcement learning was successfully applied to Cognitive Packet Network (CPN) architecture so as to offer users QoS driven packet delivery services. The experiments conducted on a 26-node testbed clearly demonstrated the learning capability of the RNNs in CPN.