Projects / Programmes
Towards the environment-aware intelligent wireless communications
| Code |
Science |
Field |
Subfield |
| 2.08.00 |
Engineering sciences and technologies |
Telecommunications |
|
| Code |
Science |
Field |
| 2.02 |
Engineering and Technology |
Electrical engineering, Electronic engineering, Information engineering |
intelligent wireless networks, resource management and optimization, radio channel modelling, environment awareness, energy efficiency, radio wave exposure, indoor localization, radio channel database
Data for the last 5 years (citations for the last 10 years) on
April 24, 2024;
A3 for period
2018-2022
Data for ARIS tenders (
04.04.2019 – Programme tender,
archive
)
| Database |
Linked records |
Citations |
Pure citations |
Average pure citations |
| WoS |
175 |
1,508 |
1,325 |
7.57 |
| Scopus |
289 |
2,746 |
2,404 |
8.32 |
Researchers (11)
Organisations (1)
| no. |
Code |
Research organisation |
City |
Registration number |
No. of publicationsNo. of publications |
| 1. |
0106 |
Jožef Stefan Institute |
Ljubljana |
5051606000 |
90,724 |
Abstract
The main mission of the former wireless communications was to provide communications between human users. Today, 4G wireless communications enable the interaction between human users and centrally-located content and service providers, such as video streaming, on line shopping, etc, while the vision of coming 5G is to extend the communication beyond human user and include machine type communications, including embedded devices used in the internet of things concept. Though the wireless networks provide the communication between intelligent devices, the network itself is still not intelligent. There is no doubt that, if the target objectives of the 5G networks and beyond want to be achieved, the wireless network itself should become intelligent meaning that the actions in wireless networks are executed based on the experience and outcome of past actions and latest information about the radio environment status. The intelligence should be built in every layer of protocol stack from physical to application layer in order to force network to become intelligent, but this is a huge task, which goes beyond the human and financial resources provided by this call. For that reason, we are limiting our research to the tasks related to physical layer, in particular, to the support of environmental information for the estimation and prediction of the channel state information (CSI), with emphasis on indoor wireless communications. In this respect, the project main goal is to develop a novel methodology which enables prediction of the radio channels properties beyond what is currently available, by taking the advantage of environmental information, measured channel state information (CSI) and information about the radio nodes. The project goals will be achieved by addressing the following main objectives namely, (i) the deep survey of the system requirements of environment aware intelligent wireless networks, (ii) the system architecture design which applies model-driven and data-driven approaches to predict the CSI from environmental information and from CSI estimates obtained from the training symbols, (iii) proposing and performance evaluation of new, advance methods, algorithms and approaches that enables the intelligent and environmentally friendly (to nature and people) usage of radio resources taking into account the environmental information for indoor communication with focus on algorithms for radio nodes localization, radio environment classification applying measured CSI and extensive measurement databases and algorithms complementing the CSI and environmental information and (iv) proving of the proposed concept on a Log-A-Tec testbed applying UWB radio technology and evaluating the proposed solution in the view of energy-efficiency, environmental friendliness and intelligence in real environment. In order to evaluate the proposed solution the following key performance indicators (KPI) will be considered, (i) the decrease in training symbol transmission and thus improved link capacity due to usage of environmental information and intelligence in the network, (ii) the decrease of information latency due to known channel state information, (iii) the decrease in amount of energy consumed in the energy efficient intelligent, environment aware wireless networks and (iv) the decrease in the exposure of people and animals to non-ionised radio wave radiation. We do believe that by complementing the estimation of the CSI from training symbols with environmental information, we can improve the accuracy of the CSI prediction and consequently increase the net capacity of the communication link. Furthermore, data driven radio environment classification decrease time for CSI estimation, and contribute to the target objective of the 5G networks and beyond, such as order of magnitude increases in mobile data volume per area, number of connected devices, typical user data rate and latency close to 1ms.
