A Multi Layer Perceptron Based Throughput Prediction Technique using MDT Data and Physical Layer Measurements 


Vol. 43,  No. 5, pp. 808-816, May  2018
10.7840/kics.2018.43.5.808


PDF
  Abstract

In this paper, we analyze the relationship between various physical layer measurements including MDT data and throughput, and propose a multi layer perceptron(MLP) based throughput prediction method using the physical layer measurements. First, we analyze and select various physical layer measurements that affect the transmission rates to the UE in the LTE network using the actual measurements. In addition, we construct a MLP model for throughput prediction and train the prediction model using the physical layer measurements with throughput. From the simulation results, it is shown that the throughput prediction model based on the MLP shows the similar actual measured throughput, and has the improved results compared to other prediction techniques.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

J. Park, D. Kim, G. Kong, S. Choi, "A Multi Layer Perceptron Based Throughput Prediction Technique using MDT Data and Physical Layer Measurements," The Journal of Korean Institute of Communications and Information Sciences, vol. 43, no. 5, pp. 808-816, 2018. DOI: 10.7840/kics.2018.43.5.808.

[ACM Style]

Junggyun Park, Dongwook Kim, Gyuyeol Kong, and Sooyong Choi. 2018. A Multi Layer Perceptron Based Throughput Prediction Technique using MDT Data and Physical Layer Measurements. The Journal of Korean Institute of Communications and Information Sciences, 43, 5, (2018), 808-816. DOI: 10.7840/kics.2018.43.5.808.

[KICS Style]

Junggyun Park, Dongwook Kim, Gyuyeol Kong, Sooyong Choi, "A Multi Layer Perceptron Based Throughput Prediction Technique using MDT Data and Physical Layer Measurements," The Journal of Korean Institute of Communications and Information Sciences, vol. 43, no. 5, pp. 808-816, 5. 2018. (https://doi.org/10.7840/kics.2018.43.5.808)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880