Fig 2 - uploaded by Darwin Aguilar
Content may be subject to copyright.
Source publication
This paper describes the methodology used to find a new semi-empirical propagation model based on received power measurements around a University Campus. The proposed model is then compared with other well known propagation models to determine its performance in the working frequency band from 5.725 to 5.85 GHz. Results indicate that the error obta...
Similar publications
It is known that the OFDM modulation is very suitable for very high-speed wireless transmission systems because of its bandwidth efficiency and ability in dealing with multipath fading. Still, large peak to average power ratio (PAPR) of an OFDM signal limits the OFDM system application to a certain degree. Peak windowing is an effective PAPR reduct...
Citations
... Traditionally, the development of wireless channel propagation models is classified as Theoretical, based on mathematical analysis [1]; Empirical, based on measurements of received signal levels; and Semiempirical, as a mixture of the previous ones [2]. Examples of these models are the Flat Earth, Cost 231, and SUI propagation models, respectively [3], allowing defining propagation models used for planning wireless networks. Additionally, the development of traditional Machine Learning Theory in conjunction with reception level measurements are presented as an alternative approach to continue with the development of propagation models, where input, output, and model specifications are identified as the main challenges of this new alternative solution [4]. ...
... The Universidad de las Fuerzas Armadas -ESPE has deployed a WiMAX network in conformance with IEEE 802.16-2009 standard, which works in the 5.8 GHz frequency band, on which measurements of the power received as a function of distance in different sectors of the university campus [3]. The database contains 185 defined points, on which nine measurements were made at each end by using a spectrum analyzer, which also has labels indicating the different scenarios on the university campus, such as streets, fields, buildings, and vegetation. ...
... Next, figure 7 shows the curve made by the autoencoder of the losses in dB compared to the measurement points in meters; in turn, it is compared with different models such as Free Space, SUI, and ESPE_Model. These models were previously compared in [3]. What is done is add the autoencoders to compare their result. ...
... There are several previously proposed semi-empirical modeling works, for example, in [7], made an adjustment of the semi-empirical prediction method COST-231 Okumura-Hata, based on experiments at 2.3GHz using WiMAX transmissions carried out in the west of India, better results were obtained, compared to the original COST-231 Okumura-Hata model; in another work [13], a semi-empirical propagation model is described based on reception power measurements obtained within the Universidad de las Fuerzas Armadas -ESPE in the 5.2 to 5.8GHz band with WiMAX technology; and in [6] a semi-empirical propagation model based on Received Signal Strength Indicator (RSSI) measurements is presented for a point-to-point link in the 2.4 GHz band, using Zigbee technology, which presents a discontinuity of decreasing exponential behavior , caused by the height of the antennas of the devices, which is better explained in [6]. ...
... The database [13] is used, the samples were taken in 184 points and each point have 9 measurements, giving a total of 1656 measurements. The place where these measurements were made in ESPE campus, this allows the data set to be divided into environments. ...
... where: P R are the measured powers at the receiver, P T = 22dBm is the power transmitter, the gains of the antennas G R and G T are 7dBi, the losses of the cables L ω R and connectors L ω L are 1.75dB, and the channel losses are represented by L M [13].The model presented by the authors is called ESPE-Model, described according to the expression: ...
Wireless networks are one of the most important technologies worldwide, as modeling the different telecommunication channels is an active task of several groups of researchers. Obtaining a theoretical or semi-empirical model of a channel allows improving the planning of wireless networks. The proposed methodology allows channels to be modeled semi-empirically using machine learning tools. This article presents the use of Machine Learning techniques as a tool for describing wireless channels in the 2.4 GHz and 5.8 GHz bands with Zigbee and WiMAX technologies, respectively. This allows to develop a more accurate propagation model, in addition with the generation of heat maps and more reliable schedules. A synthetic data generation technique is proposed, in order to train the Support Vector Machines algorithms of Regression Learning, with this, two semi-empirical models are generated with a lower Root Mean Square Error of 1.4% for Zigbee, and 13,84% for WiMAX, with respect to traditional models.
