KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Access type: UnknownAuthor: search.filters.author.Jaruvitayakovit, Tanun

Search Results

Now showing 1 - 5 of 5
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Deep Learning Aided Robust RSRP Prediction in Cellular Networks
    (2024-01-01)
    Wongphatcharatham, Tanutsorn
    ;
    Phakphisut, Watid
    ;
    Jaruvitayakovit, Tanun
    ;
    Boonkajay, Amnart
    ;
    Huang, Jiajia
    We propose a transfer learning enhanced hybrid model for robust reference signal received power (RSRP) prediction. The hybrid model comprises an expected RSRP estimation based on transmit power, 3-D antenna gain models, path loss, and a deep learning (DL) for predicting an error from ground-truth measurement. The DL architecture consists of regression neural network (NN) and convolutional neural network (CNN). Besides cell site configuration and the long-term evolution (LTE) measurement report from user equipments (UEs), the expected RSRP and geospatial data e.g. building percentage and clutter index are considered. Since trained model may not perform well in new environment, it requires tedious work and long time to collect data at a new cell site. Therefore, we use transfer learning (TL) to apply the trained model to the other areas, which have differences in environment information and antenna configurations, by transferring the knowledge acquired from trained model. The results of the trained area show that root mean square error (RMSE) and mean absolute error (MAE) are approximately 2.92 and 2.01, respectively. For the other area, TL have improved MAE approximately 1 to 2.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Reference Signal Received Power Prediction Using Convolutional Neural Network with Residual Loss
    (2023-01-01)
    Ngenjaroendee, Thearrawit
    ;
    Phakphisut, Watid
    ;
    Wijitpornchai, Thongchai
    ;
    Areeprayoonkij, Poonlarp
    ;
    Jaruvitayakovit, Tanun
    In this paper, LTE measurement reports collected from user equipments are used to generate the residual loss, which can represent the loss value of each grid. The residual loss and geospatial data are used in the learning process of convolutional neural network (CNN). We also use the site configuration and three-dimensional antenna pattern. Thus, the neural network and convolutional neural network are proposed to construct deep learning to predict the reference signal received power (RSRP) in Bangkok, Thailand. The results show that residual loss can improve the efficiency of prediction.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Multi-Agent Q-Leaming for Power Allocation in Interference Channel
    (2022-01-01)
    Wongphatcharatham, Tanutsorn
    ;
    Phakphisut, Watid
    ;
    Wijitpornchai, Thongchai
    ;
    Areeprayoonkij, Poonlarp
    ;
    Jaruvitayakovit, Tanun
    Signal transmission in wireless networks suffers from unwanted interference. To maximize signal to interference plus noise ratio, transmit power of each transmitter needs to be optimally allocated. Here, we propose to use multi-agent Q-learning to optimize such transmit power within interference channel. Our simulation indicated that multi-agent Q-Iearning resulted in better sum-rate than the traditional methods such as the maximum power allocation and the random power allocation. Our work offers a novel and practical computational approach to optimizing signal transmission in wireless networks.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Clustering Technique for Constructing Path Loss Model in Bangkok Metropolis
    (2022-01-01)
    Chomsuay, Danupol
    ;
    Phakphisut, Watid
    ;
    Wijitpornchai, Thongchai
    ;
    Areeprayoonkij, Poonlarp
    ;
    Jaruvitayakovit, Tanun
    This paper presents the path loss model for any areas of Bangkok metropolis. In general, the path loss models can be divided into three main categories: rural, suburban, and urban. However, in this work, we propose the clustering technique which can divide Bangkok metropolis into many areas. Then, the path loss model is designed according to the characteristics of each area. We use the standard propagation model (SPM) to design the path loss. We also use the least square method for finding the optimal parameter of SPM. The results show that our BK900 model, BK1800 model, and BK2100 model can provide the RMSE around 2.9 dB, 3.2 dB, and 4.8 dB, respectively.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Deep Learning-based Reference Signal Received Power Prediction for LTE Communication System
    (2022-01-01)
    Ngenjaroendee, Thearrawit
    ;
    Phakphisut, Watid
    ;
    Wijitpornchai, Thongchai
    ;
    Areeprayoonkij, Poonlarp
    ;
    Jaruvitayakovit, Tanun
    A highly accurate prediction of radio signal power is crucial for planning the coverage of mobile networks. Currently, a path loss model is most widely used to predict the radio signal. However, the path loss models commonly provide an over-or under-estimation of the signal power. In this paper, we present the reference signal received power (RSRP) prediction using a deep learning. To evaluate the performance of our prediction system, we use the empirical data in Bangkok metropolitan area. Especially, the empirical data comprise 2 million measurements per day for deep learning. The root mean square error (RMSE) value of our prediction is approximately 3.91 dB.