Time series forecasting model of future spectrum demands for mobile broadband networks in Malaysia, Turkey, and Oman

Ibraheem Shayea, Abdulraqeb Alhammadi*, Ayman A. El-Saleh, Wan Haslina Hassan, Hafizal Mohamad, Mustafa Ergen

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

8 Citations (Scopus)


Mobile broadband (MBB) services are rapidly growing, causing a massive increase in mobile data traffic growth. This surge in data traffic is due to several factors (such as the massive increase of subscribers, mobile applications, etc.) which have led to the need for more bandwidth. Mobile service providers are constantly improving their network efficiency by upgrading current networks and investing in newer mobile network generations. However, these improvements will not be enough to accommodate the future spectrum demands. This paper proposes a time series forecasting model to analyze future spectrum demands based on the spectrum efficiency growth of MBB networks. This model depends on two key input data: the average spectrum efficiency per site and the number of sites per technology. The model is used to predict the spectrum efficiency growth of three countries (Turkey, Malaysia, and Oman) from 2015 to 2025. The proposed model is compared with various traditional statistical models such as the Moving Average (MA), Auto-Regression (AR), Autoregressive–Moving-Average (ARMA), and Autoregressive Integrated Moving Average (ARIMA). The forecasted results indicate that the average spectrum efficiency and growth will continue to rise multiple times by 2025 compared to 2015. The data from this prediction model can be used as input data to forecast the required spectrum needed in future for any specific country. This study further contributes to the network planning of future mobile networks for Fifth Generation (5G) and Sixth Generation (6G) technology. The proposed model obtains higher accuracy (by 90%) compared to other models. The proposed model is also applicable to any country, especially when new wireless communication technologies emerge in future. It is customizable and scalable since spectrum regulators can add additional metrics that positively contribute towards accurately estimating future spectrum efficiency growth.

Original languageEnglish
Pages (from-to)8051-8067
Number of pages17
JournalAlexandria Engineering Journal
Issue number10
Publication statusPublished - Oct 2022

Bibliographical note

Publisher Copyright:
© 2022


The research leading to these results has received funding from The Research Council (TRC) of the Sultanate of Oman under the Block Funding Program with agreement no. TRC/BFP/ASU/01/2019. This study was also sponsored by Universiti Teknologi Malaysia through the Professional Development Research University Grant (No. 05E92). The conducted research has also benefitted from the 2232 International Fellowship for Outstanding Researchers Program of TÜBİTAK (Project No: 118C276) conducted at Istanbul Technical University (ITU), and supported by the Malaysian Ministry of Higher Education Fundamental Research Grants No. FRGS/1/2021/TK02/USIM/01/1.

FundersFunder number
Malaysian Ministry of Higher Education Fundamental ResearchFRGS/1/2021/TK02/USIM/01/1
Norges ForskningsrådTRC/BFP/ASU/01/2019
Universiti Teknologi Malaysia05E92, 118C276


    • 5G network planning
    • 6G network planning
    • Data traffic
    • Mobile broadband
    • Spectral efficiency
    • Spectrum demand
    • Spectrum efficiency growth
    • Spectrum forecasting


    Dive into the research topics of 'Time series forecasting model of future spectrum demands for mobile broadband networks in Malaysia, Turkey, and Oman'. Together they form a unique fingerprint.

    Cite this