Delay in data transmission is one of the key performance indicators (KPIs) of a network. The planning and design value of delay in network management is of crucial importance for the optimal allocation of network resources and their performance focuses. To create optimal solutions, predictive models, which are currently most often based on machine learning (ML), are used. This paper aims to investigate the training, testing and selection of the best predictive delay model for a VoIP service in a Long Term Evolution (LTE) network using three ML techniques: Multilayer Perceptron (MLP), Support Vector Machines (SVM) and k-Nearest Neighbors (k-NN). The space of model input variables is optimized by dimensionality reduction techniques: RReliefF algorithm, Backward selection via the recursive feature elimination algorithm and the Pareto 80/20 rule. A three-segment road in the geo-space between the cities of Banja Luka (BL) and Doboj (Db) in the Republic of Srpska (RS), Bosnia and Herzegovina (BiH), covered by the cellular network (LTE) of the M:tel BL operator was chosen for the case study. The results show that the k-NN model has been selected as the best solution in all three optimization approaches. For the RReliefF optimization algorithm, the best model has six inputs and the minimum relative error (RE) RE = 0.109. For the Backward selection via the recursive feature elimination algorithm, the best model has four inputs and RE = 0.041. Finally, for the Pareto 80/20 rule, the best model has 11 inputs and RE = 0.049. The comparative analysis of the results concludes that, according to observed criteria for the selection of the final model, the best solution is an approach to optimizing the number of predictors based on the Backward selection via the recursive feature elimination algorithm.

Solar energy is very important means of expanding renewable energy resources. In this paper is described the design and construction of a microcontroller based solar panel tracking system. Solar tracking allows more energy to be produce because the solar array is able to remain aligned to the sun. The paper begins with presenting background theory in light sensors and stepper motors as they apply to the project. In the conclusions are given discussions of design results.

The paper proposes a Hybrid Electric Vehicle (HEV) design based on the installation of a fuel cell (FC) module in the existing Daewoo Tico electric vehicle to increase its range in urban areas. Installing an FC module supplied by a 2 kg hydrogen tank would not significantly increase the mass of the electric vehicle, and the charging time of the hydrogen tank is lower than the battery charging time. For design analysis, a model was created in the MATLAB/Simulink software package. The model simulates vehicle range at different HEV speeds for Absorbent Glass Mat (AGM) and Proton Exchange Membrane Fuel Cell (PEMFC) power sources. The greatest anticipated benefit derived from the model analysis relates to velocities ranging from 20 km/h to 30 km/h, although the optimal HEV velocity in an urban area is in the range of 30 km/h to 40 km/h. The results indicate that this conversion of Electric Vehicle (EV) to HEV would bring a benefit of 87.4% in terms of vehicle range in urban areas. Therefore, the result of the conversion in this case is a vehicle with sub-optimal characteristics, which are nevertheless very close to optimal.

The main goal of this paper is to create an adaptive model based on multilayer perceptron (MLP) for prediction of average downlink (DL) data throughput per user and average DL data throughput per cell within an LTE network technology and in a geo-space that includes a segment of the Motorway 9th January with the access roads. The accuracy of model prediction is estimated based on relative error (RE). With multiple trainings and testing of 30 different variants of the MLP model, with different metaparameters the final model was chosen whose average accuracy for the Cell Downlink Average Throughput variable is 89.6% (RE = 0.104), while for the Average User Downlink Throughput variable the average accuracy is 88% (RE = 0.120). If the coefficient of determination is observed, the results showed that the accuracy of the best selected prediction model for the first variable is 1.4% higher than the accuracy of the prediction of the selected model for the second dependent variable. In addition, the results showed that the performance of the MLP model expressed over R² was significantly better compared to the reference multiple linear regression (MLR) model used.