EconPapers    
Economics at your fingertips  
 

An AI-Driven Energy-Saving Framework for Multi-Vendor 4G/5G Networks: Predictive Sleep Control for Greener Mobile Operations in Saudi Arabia

Siddiq Bin Salam and Sajjad Waqar Ahmed
Additional contact information
Siddiq Bin Salam: Saudi Telecom Company, Saudi Arabia
Sajjad Waqar Ahmed: Saudi Telecom Company, Saudi Arabia

Technium Sustainability, 2026, vol. 11, 148-163

Abstract: The rapid densification of 4G and 5G radio access networks (RAN) across the Kingdom of Saudi Arabia is driving a steep rise in energy consumption and operating expenditure, placing telecom operations in direct tension with the decarbonisation commitments of the Saudi Green Initiative and the Kingdom's 2060 net-zero target. The RAN is the dominant energy consumer in a mobile network, and conventional static energy-saving features are poorly matched to the extreme diurnal traffic and temperature swings of the Arabian Peninsula, where ambient heat both raises baseline power draw and inflates cooling load. This paper proposes the Hierarchical RAN Energy Optimization (HREO) framework, a three-tier, AI-driven, multi-vendor architecture that converts energy efficiency from a static configuration into a predictive, closed-loop control problem. A reactive cell tier exposes the advanced sleep modes (SM1–SM4) of heterogeneous Tier-1 vendor equipment; a predictive AI tier, hosted as a Near-RT RIC xApp, pairs a per-cell LSTM traffic forecaster with a reinforcement-learning sleep-policy agent whose reward explicitly trades energy saving against a hard quality-of-service penalty and a switching-cost term; and a network orchestration tier distributes policy across the multi-vendor estate through the O-RAN O1 interface and prioritises sites powered by solar-battery micro-grids. The framework is localised to Saudi conditions through a temperature-dependent power model and a high-irradiance solar profile, and all targets are expressed against published vendor power ratings and 3GPP baselines rather than proprietary operator data. The result is a deployable, vendor-neutral pathway that aligns national RAN operations with the Saudi Green Initiative while protecting user experience.

Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://techniumscience.com/index.php/sustainability/article/view/13740 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:tec:sustai:ojs:13740

DOI: 10.47577/sustainability.v11i.13740

Access Statistics for this article

Technium Sustainability is currently edited by Tasente Tanase

More articles in Technium Sustainability from Technium Science
Bibliographic data for series maintained by Tasente Tanase ( this e-mail address is bad, please contact ).

 
Page updated 2026-10-16
Handle: RePEc:tec:sustai:ojs:13740