The author investigated traffic flow quality on a new 2+1 long road bypass with an exceptionally high share of heavy vehicles in order to assess rational limits of heavy vehicle shares in traffic flow, dependent on the length of the 2+1 road and the number of passing segments in each direction. This paper presents the results of traffic flow quality analyses through the use of empirical and simulation methods for a single 2+1 road segment with additional passing lanes, as well as for the study of the entire section of the bypass – 2+1 road. Variables include analysis of travel speed distribution, platoon traffic, and amount of passing maneuvers. Results show that large passing demands lead to very high speeds (over 100 km/h) on segments with additional passing lanes. The conclusions include remarks related to the use and operation of 2+1 cross-sections with high shares of heavy vehicles.

One of the basic parameters which describes road traffic is Annual Average Daily Traffic (AADT). Its accurate determination is possible only on the basis of data from the continuous measurement of traffic. However, such data for most road sections is unavailable, so AADT must be determined on the basis of short periods of random measurements. This article presents different methods of estimating AADT on the basis of daily traffic (VOL), and includes the traditional Factor Approach, developed Regression Models and Artificial Neural Network models. As explanatory variables, quantitative variables (VOL and the share of heavy vehicles) as well as qualitative variables (day of the week, month, level of AADT, the cross-section, road class, nature of the area, spatial linking, region of Poland and the nature of traffic patterns) were used. Based on comparisons of the presented methods, the Factor Approach was identified as the most useful.

High concentrations of nitrogen dioxide in the air, particularly in heavily urbanized areas, have an adverse eff ect on many aspects of residents’ health. A method is proposed for modelling daily average, minimal and maximal atmospheric NO ₂ concentrations in a conurbation, using two types of modelling: multiple linear regression (LR) an advanced data mining technique – Random Forest (RF). It was shown that Random Forest technique can be successfully applied to predict daily NO ₂ concentration based on data from 2015–2017 years and gives better fit than linear models. The best results were obtained for predicting daily average NO ₂ values with R ² =0.69 and RMSE=7.47 μg/m . The cost of receiving an explicit, interpretable function is a much worse fit (R ² from 0.32 to 0.57). Verification of models on independent material from the first half of 2018 showed the correctness of the models with the mean average percentage error equal to 16.5% for RF and 28% for LR modelling daily average concentration. The most important factors were wind conditions and traffic flow. In prediction of maximal daily concentration, air temperature and air humidity take on greater importance. Prevailing westerly and south-westerly winds in Wrocław effectively implement the idea of ventilating the city within the studied intersection. Summarizing: when modeling natural phenomena, a compromise should be sought between the accuracy of the model and its interpretability.

This article deals with issues related to the optimization of traffic management in modern cities, the so-called Smart City. In particular, the article presents the process of evolution of the traffic flow prediction model at a selected crossroads in a selected city in Poland - the city of Rzeszów. Rzeszow is an example of a smart city equipped with an extensive system of real-time data collection and processing from multiple road points in the city. The research was aimed at a detailed analysis of the feasibility and degree of fit of different variants of the regression model: linear, polynomial, trigonometric, polynomial-trigonometric, and regression-based Random Forest algorithm. Several studies were carried out evaluating different generations of models, in particular, an analysis was carried out based on which the superiority of the trigonometric model was demonstrated. This model had the best fit and the lowest error rate, which could be a good conclusion for widespread use and implementation in Smart City supervisory systems.

The Traffic Flow Description (TFD) option of the IP protocol is an experimental option, designed by the Authors and described by the IETF’s Internet Draft. This option was intended for signalling for QoS purposes. Knowledge about forthcoming traffic (such as the amount of data that will be transferred in a given period of time) is conveyed in the fields of the option between end-systems. TFD-capable routers on a path (or a multicast tree) between the sender and receiver(s) are able to read this information, process it and use it for bandwidth allocation. If the time horizons are short enough, bandwidth allocation will be performed dynamically. In the paper a performance evaluation of an HD video transmission QoS assured with the use of the TFD option is presented. The analysis was made for a variable number of video streams and a variable number of TCP flows that compete with the videos for the bandwidth of the shared link. Results show that the dynamic bandwidth allocation using the TFD option better assures the QoS of HD video than the classic solution, based on the RSVP protocol.