Network planning and design

About: Network planning and design is a research topic. Over the lifetime, 12393 publications have been published within this topic receiving 229776 citations. The topic is also known as: network design.

A Long Short-Term Memory Recurrent Neural Network Framework for Network Traffic Matrix Prediction

Abstract: Network Traffic Matrix (TM) prediction is defined as the problem of estimating future network traffic from the previous and achieved network traffic data. It is widely used in network planning, resource management and network security. Long Short-Term Memory (LSTM) is a specific recurrent neural network (RNN) architecture that is well-suited to learn from experience to classify, process and predict time series with time lags of unknown size. LSTMs have been shown to model temporal sequences and their long-range dependencies more accurately than conventional RNNs. In this paper, we propose a LSTM RNN framework for predicting Traffic Matrix (TM) in large networks. By validating our framework on real-world data from G ´ EANT network, we show that our LSTM models converge quickly and give state of the art TM prediction performance for relatively small sized models.

Method and apparatus for modeling a smart antenna in a network planning tool

Abstract: A network planning tool (NPT) computer program is used to model characteristics of a wireless telephone network (10). The network contains a plurality of cells (12) which each include a plurality of sectors (16-18) disposed about a base station (13) that has a respective antenna for each sector. Techniques are provided for modeling smart antennas (131), including use of a switched-beam transmit and receive patterns with approximately random allocation among the beams of frequencies assigned to an associated sector. In the case of an adaptive beam-forming smart antenna, power levels for that antenna and a remote antenna operating at the same frequency are adjusted so as to increase a differential therebetween by an improvement value associated with the smart antenna. Potential uplink interference at a given base station is modeled by simulating operation of other base stations at an uplink frequency with a reduced power level. Potential interfering signals are discounted to the extent a smart antenna can intelligently reject a limited number of undesired signals.

Routing, spectrum and core allocation in flexgrid SDM networks with multi-core fibers

Abstract: Space division multiplexing (SDM) over multi-core fiber (MCF) is advocated as a promising technology to overcome the capacity limit of the current single-core optical networks. However, employing the MCF for flexgrid networks necessitates the development of new concepts, such as routing, spectrum and core allocation (RSCA) for traffic demands. The introduction of MCF in the networks mitigates the spectrum continuity constraint of the routing and spectrum assignment (RSA) problem. In fact cores can be switched freely on different links during routing of the network traffic. Similarly, the route disjointness for demands with same allocated spectrum diminishes to core disjointness at the link level. On the other hand, some new issues such as the inter-core crosstalk should be taken into account while solving the RSCA problem. This paper formulates the RSCA network planning problem using the integer linear programming (ILP) formulation. The aim is to optimally minimize the maximum number of spectrum slices required on any core of MCF of a flexgrid SDM network. Furthermore, a scalable and effective heuristic is proposed for the same problem and its performance is compared with the optimal solution. The results show that the proposed algorithm is able to well approximate the optimal solution based on ILP model.