Accurate channel models are essential to evaluate mobile communication system performance and optimize coverage for existing deployments. The introduction of various transmission frequencies 5G imposes new challenges accurate radio prediction. This paper compares traditional a model obtained using Deep Learning (DL)-techniques utilizing satellite images aided by simple path loss model. Experimental measurements gathered compose the training test set. considers modelling techniques offered...

Linear signal processing algorithms are effective in dealing with linear transmission channel and detection, whereas the nonlinear algorithms, from machine learning community, detection. In this paper, a brief overview of various methods their application optical communication is presented discussed. Moreover, supervised methods, such as neural networks support vector machine, experimentally demonstrated for in-band to noise ratio estimation modulation format classification, respectively....

Methods for accurate prediction of radio signal quality parameters are crucial optimization mobile networks, and a necessity future autonomous driving solutions. The power-distance relation current empirical models struggles with describing the specific local geo-statistics that influence parameters. use commonly results in an overor under-estimation require additional calibration studies. In this paper, we present novel model-aided deep learning approach path loss prediction, which...

Gaussian process regression is numerically and experimentally investigated to predict the bit error rate of a 24 × 28 GBd QPSK WDM system. The proposed method produces accurate predictions from multi-dimensional sparse measurement data.

Drive testing is a common practice performed by operators to optimize and evaluate their mobile networks with respect capacity coverage. For dense areas, drive test measurements are very time-consuming due many obstacles causing Non-Line-Of-Sight (NLoS) scenarios. In this paper, we show how Deep Learning (DL) techniques can be utilized predict LTE signal quality metrics using measurements. Moreover, the obtained solution offer insight into where additional required. The proposed accurately...

Reliable connectivity over large distances is one of the main features characterising Low-Power Wide Area Network (LP-WAN) technologies, with Narrowband Internet Things (NB-IoT) as most promising one. The advent such a family communication standards has attracted attention industry, excellent coverage LP-WAN potentially enables new opportunities automation, for instance remote metering or asset tracking. However, telecommunication standardisation bodies are still lacking accurate models...

Linear signal processing algorithms are effective in combating linear fibre channel impairments. We demonstrate the ability of machine learning to combat nonlinear impairments and perform parameter extraction from directly detected signals.

In this work we investigate signal strength and quality of Narrowband Internet Things (NB-IoT) in a marine environment. particular, demonstrate the suitability NB-IoT technology as carrier for maritime applications, where water boat masts can potentially affect transmission.

Accurate channel models for predicting received power under slow fading impairments are essential planning 5G solutions due to the increased range of possible transmission frequencies. The densification base stations will pose an number complex coverage and capacity situations where flexible computational simple essential. In this paper, we study state-of-the-art empirical models, more specifically ITU-R M.2412 3GPP 38.901, their performance on experimental measurements at 2630 MHz LTE-A...

Critical Internet-of-Things (IoT) services require seamless connectivity, which is not always simple to provide and particularly in deep-indoor scenarios, it can be even impossible some cases. The existing outdoor-to-indoor path-loss models lack accuracy underground situations, thus IoT coverage planning such areas cannot rely on robust tools becomes a process of trial error. In this work, we derive analyze various environmental features that useful understanding sub-GHz signal propagation....

Datacenter networks are becoming crucial foundations for our information technology based society. However, commercial datacenter infrastructure is often unavailable to researchers conducting experiments. In this work, we therefore elaborate on the possibility of combining hardware and simulation illustrate scalability performance networks. We simulate a network interconnect it with real world traffic generation hardware. Analysis introduced packet conversion virtual queueing delays shows...

Internet of Things (IoT) applications are becoming more and popular for the transmission sensor data in various environments. Due to required battery lifetime, Low-Power WAN technologies such as NB-IoT LoRaWAN promising candidates provide connectivity so called deep-indoor In this paper, we compare these two terms Received Signal Strength Indicator (RSSI) a practical field test simulation study.

Path-loss modelling in deep-indoor scenarios is a difficult task. On one hand, the theoretical formulae solely dependent on transmitter-receiver distance are too simple; other discovering all significant factors affecting loss of signal power given situation may often be infeasible. In this paper, we experimentally investigate influence features such as indoor depth, and to closest tunnel corridor effect received using NB-IoT. We describe measurement campaign performed system long...

In this paper, machine learning techniques relevant to optical communication are presented and discussed. The focus is on applying tools performance monitoring prediction.

Traffic growth in mobile networks is posing challenges not only from the point of view capacity demands, but also power consumption. At same time, are becoming increasingly complex, with heterogeneous tiers Base Stations (BSs) and different technologies. Autonomous self-adapting saving schemes that take into account a large number network metrics have been proposed to address these aspects. However, performances applications running user terminals can be negatively affected by aim at...

Methods for accurate prediction of radio signal quality parameters are crucial optimization mobile networks, and a necessity future autonomous driving solutions. The power-distance relation current empirical models struggles with describing the specific local geo-statistics that influence parameters. use commonly results in an over- or under-estimation require additional calibration studies. In this paper, we present novel model-aided deep learning approach path loss prediction, which...

Path-loss modelling in deep-indoor scenarios is a difficult task. On one hand, the theoretical formulae solely dependent on transmitter-receiver distance are too simple; other discovering all significant factors affecting loss of signal power given situation may often be infeasible. In this paper, we experimentally investigate influence features such as indoor depth, and to closest tunnel corridor effect received using NB-IoT. We describe measurement campaign performed system long...