AI-Based Base Station Power Control for Energy Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In ultra-dense networks, the energy efficiency of base stations is degraded due to a large number of stations with low or no traffic load, leading to severe inter-cell interference and high calculation complexity in determining optimal active/sleep modes.
Innovation Solution
A method is introduced where base stations with low traffic load transition to a sleep mode, utilizing artificial intelligence-based power control through deep reinforcement learning to optimize energy efficiency and reduce calculation complexity by determining active/sleep modes based on channel state information and quality of service indicators.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If base stations are densely deployed to improve network capacity, then network capacity is improved, but energy efficiency is degraded due to low traffic load
Solution Approach 1:
The base station operates in dynamic active and sleep modes, transitioning between states based on traffic conditions. This dynamic operation allows the system to maintain high network capacity through dense deployment while improving energy efficiency by switching low-traffic base stations to sleep mode, thereby resolving the contradiction between network capacity and energy efficiency.
2Productivity
If base stations are deployed in large numbers to improve network capacity, then network capacity is improved, but inter-cell interference becomes severe
Solution Approach 1:
Base stations periodically transition between active and sleep modes based on traffic patterns. This periodic operation reduces the number of simultaneously active base stations, thereby reducing inter-cell interference while maintaining overall network capacity through time-division multiplexing of network resources.
3Use of energy by moving object
If optimal active/sleep modes are determined to improve energy efficiency, then energy efficiency is improved, but calculation complexity increases
Solution Approach 1:
Each base station autonomously determines its own active/sleep mode based on local traffic conditions and pre-configured thresholds, eliminating the need for complex centralized optimization calculations. This self-service approach improves energy efficiency through decentralized decision-making while significantly reducing calculation complexity.
4Use of energy by moving object
If base stations transition to sleep mode to reduce power consumption, then power consumption is reduced, but quality of service may be degraded
Solution Approach 1:
The system continuously monitors traffic conditions and base station states, using this feedback to dynamically adjust active/sleep mode transitions. This feedback mechanism ensures that base stations remain active when quality of service requirements are high while transitioning to sleep mode when traffic demand is low, thereby reducing power consumption without degrading quality of service.
Data Source
AI summary
The disclosure relates to a 5G communication system or a 6G communication system for supporting higher data rates beyond a 4G communication system such as long term evolution (LTE). The disclosure relates to a technique for controlling a base station power using an artificial intelligence based technology to improve an energy efficiency of a communication network. A method performed by a base station of a communication system according to an embodiment of the disclosure may include acquiring state information, determining an active/sleep request indicator (ASRI) based on at least a part of the state information, transmitting at least one of the state information and the ASRI to a central unit, receiving, from the central unit, power control information determined based on the at least one of the state information and the ASRI, and performing a power control based on the received power control information.