Search

Ensuing from the deteriorating conditions of road networks, traffic forecasting techniques with mathematical and computer-theory methods have been employed to address the real-time prediction of traffic conditions and their dynamic control, with the optimum use of the current infrastructure. The prediction of traffic conditions, acknowledging multiple regimes, its transitions and driver’s behaviour parameters, is a highly desired attribute in intelligent transportation systems (ITS), as it could increase operational performance. The study in question aims to provide a framework to define the reasons that might preserve the conditions of recurrent and non-recurrent congestion occurrence in highways, so as to develop in long term an efficient dynamic traffic prediction model that would mitigate congestion emergence, before being triggered by interactive exogenous parameters, such as weather conditions, traffic composition, incident occurrence, traffic direction and seasonality. Contrary to currently existent prediction models, the challenge of the model to be developed is to capture traffic dynamics and enhance predictability upon multiregime (congestion, near-congestion, free flow) and transitional traffic behaviour, combining exogenous multi-dimensional determinants with real-time or near-real-time data, resulting to dynamic prediction models for highway traffic. Apart from the dynamic aspect, the transferability issue will be attempted to be addressed. Furthermore, active traffic management (ATM) highway management schemes will be formed in microscopic scale, with principal goal to control traffic by optimising the operation of an emergency lane as additional traffic lane.

Incremental planning is performed periodically to decide how a backbone optical network has to be updated to serve the forecast traffic during the next planning period. Based on reliable traffic prediction, new equipment is installed and its capacity is ready to be used. Nonetheless, due among others to the introduction of new services, exact prediction is not usually available, which leads to installing more capacity than that required thus, increasing network expenditures. To reduce expenses, in this paper we propose to increment the capacity of the network as soon as it is required to meet the target performance. Hence, performance metrics are monitored and the incremental capacity (INCA) planning problem is solved on- demand when some drops under a threshold. The INCA problem is mathematically modelled and a heuristic algorithm is proposed to solve the problem in practical times. In view of the INCA problem needs to access both, operation and inventory databases, an architecture to support on-demand network planning as well as a model for the inventory is proposed. Exhaustive simulation results together with its experimental assessment validate the proposed on-demand incremental network capacity planning.

Deep-quantile regression is leveraged to capture traffic prediction uncertainty over future network planning intervals. We show that quantile predictions, acting as discriminative margins, result to significant spectrum savings compared to empirically estimated myopic margins considered.

A traffic simulation of the Jianghan Zone in Wuhan, China was carried out. In order to simulate genuine traffic flow without traditional hard-to-implement data collection methods, geographic population distribution data were gathered from the public information and traffic flow was generated by ActivityGen in SUMO (Simulation of Urban Mobility). For the sake of discovering the accuracy of the simulated traffic, real-time road condition and traffic prediction based on previous data on same time of each road in this area was compared. The results show that traffic flow generated from geographic population distribution data has referential meanings and with more detailed model classification, simulated traffic data can be closer to real conditions. This may offer a new way to generate traffic flow for researchers working in traffic simulation area. Further improvement of the accuracy in traffic flow generation by geographic population needs to pay more attention on special places like hospital and train stations.

The introduction of new services requiring large and dynamic bitrate connectivity can cause changes in the direction of the traffic in metro and even core network segments along the day. This leads to large overprovisioning in statically managed virtual network topologies (VNT), designed to cope with the traffic forecast. To reduce expenses while ensuring the required grade of service, in this paper we propose the VNT reconfiguration approach based on current and near-future traffic matrices (VENTURE) to regularly adapt the topology to both, the current and future traffic volume and direction. The problem is formally stated and a heuristic algorithm is proposed to solve it.

Traditional statistical analysis and mining of network data are often employed to determine traffic distribution, to summarize a user's behavior patterns, or to predict future network traffic. We analyze three months of network log data from a deployed public safety trunked radio network. After data cleaning and traffic extraction, we apply the K-means algorithm and identify that three clusters of talk groups best reflect users' behavior patterns represented by the hourly number of calls. We propose a traffic prediction model by applying the classical SARIMA models on clusters of users. The predicted network traffic agrees with the collected traffic data and the proposed cluster-based prediction approach performs well compared to the prediction based on the aggregate traffic.

The task of predicting self-similar traffic of IoT network objects with a significant number of pulsations and the property of long-term dependence is considered, which makes it difficult to predict in practice. Using the methods of wavelet- and spline-extrapolation based on Haar-wavelet, quadratic and B-spline function, the results of prediction of multimedia traffic are obtained. We compare the results of traffic prediction based on the Haar-wavelet and the quadratic and B-spline function using wavelet- and spline-extrapolation. This will allow the choice of one or another extrapolation method to improve the accuracy of the prediction, while ensuring scalability and the ability to use it for various IoT applications to prevent network overloads.