ML-Based Fronthaul Compression for 5G Radio-Centralized Links
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing demand for wireless data traffic in 5G communication systems leads to higher fronthaul bandwidth requirements, which can result in capacity constraints, packet drops, and bit error rate degradations.
Innovation Solution
The implementation of a method and system that uses machine learning to determine specific parameters for User Equipment (UE), enabling compression and decompression of data transferred between radio nodes and centralized nodes over fronthaul links, thereby reducing bandwidth requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If fronthaul bandwidth is increased to meet increasing wireless data traffic demand, then data transfer capacity is improved, but system cost and infrastructure complexity increase
Solution Approach 1:
The patent extracts and removes redundant information from the fronthaul data stream by performing compression at the radio unit level. Only essential data elements are transmitted over the fronthaul interface, significantly reducing bandwidth requirements while maintaining the ability to meet increasing data traffic demands without proportionally increasing infrastructure complexity
Solution Approach 2:
The patent changes the parameter of data representation by applying machine learning-based compression algorithms that transform raw data into a more compact form. The compression ratio can be dynamically adjusted based on traffic conditions, allowing the system to adaptively optimize bandwidth usage and reduce fronthaul infrastructure requirements while maintaining productivity
2Reliability
If fronthaul bandwidth is increased to reduce packet drops, then data transfer reliability is improved, but system cost increases
Solution Approach 1:
By extracting and transmitting only compressed essential data over the fronthaul link, the patent reduces the volume of data susceptible to packet drops. The compression ensures that critical information is transmitted with minimal bandwidth consumption, improving reliability without requiring increased bandwidth infrastructure that would add complexity and cost
Solution Approach 2:
The patent performs data compression as a preliminary action before transmission over the fronthaul interface. This pre-compression reduces the data size that needs to be transmitted, thereby reducing the probability of packet drops and improving reliability before the data even enters the vulnerable fronthaul transmission medium, without requiring additional infrastructure
3Reliability
If fronthaul bandwidth is increased to reduce bit error rate, then signal quality is improved, but system cost and infrastructure complexity increase
Solution Approach 1:
The patent extracts and transmits only the most critical data elements in compressed form over the fronthaul interface. By removing redundant data that would contribute to bit errors without adding value, the system improves signal quality and reduces bit error rate while avoiding the need to increase bandwidth infrastructure complexity
Solution Approach 2:
The patent changes the data parameter from uncompressed to compressed format, which reduces the number of bits that need to be transmitted reliably. This parameter change reduces the overall bit error rate impact while maintaining data integrity, without requiring improved physical infrastructure that would increase complexity and cost
Data Source
AI summary
The present disclosure relates to a pre-5th-Generation (5G) or 5G communication system to be provided for supporting higher data rates Beyond 4th-Generation (4G) communication system such as Long Term Evolution (LTE). The present disclosure provides methods and systems for reducing fronthaul bandwidth. Embodiments herein relate to the field of wireless networks and more particularly to reducing fronthaul bandwidth during a transfer of data between at least one radio node and at least one centralized node in a wireless network. A method disclosed herein includes determining parameters specific to at least one User Equipment (UE) using a machine learning method. The method further includes transferring data between the at least one radio node and the at least one centralized node over a fronthaul link by compressing the data using the parameters that are determined using the machine learning method. The method further includes decompressing, by at least one of the at least one radio node and the at least one centralized node, the compressed data using the parameters that are determined using the machine learning method.