Autoencoder Compression of Wireless Network Measurements
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing amount of measurement data transmitted from wireless devices to network entities in cellular networks, such as RAN nodes, leads to significant network load and decreased efficiency due to overhead, affecting operations like link adaptation and handover.
Innovation Solution
Implementing a machine learning-based method using autoencoders for compressing measurement report data, allowing for dynamically configurable accuracy thresholds and frequency of data compression, with online model updates to adapt to network dynamics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If measurement data is transmitted frequently and in detail from wireless devices to network entities, then network control and optimization capability is improved, but network load and overhead increase significantly
Solution Approach 1:
The patent extracts only the essential and relevant measurement information from the complete measurement data set. By identifying and transmitting only the most critical parameters and events, the system maintains adequate network control capability while significantly reducing the volume of transmitted data, thus resolving the contradiction between measurement precision and data quantity.
Solution Approach 2:
The patent implements partial action by selectively transmitting measurement data based on predefined thresholds, events, or specific conditions rather than continuously transmitting all measurement information. This approach ensures that network entities receive sufficient data for effective control and optimization while avoiding the overhead of transmitting excessive redundant information.
2Productivity
If comprehensive measurement reports are transmitted continuously, then network optimization capability is improved, but network efficiency decreases due to overhead
Solution Approach 1:
The patent implements periodic action by transmitting measurement reports at specific intervals or triggered by particular events rather than continuously. This allows the network to maintain optimization capability through regular updates while reducing energy consumption and overhead by avoiding constant data transmission, thus resolving the contradiction between productivity and energy loss.
3Measurement precision
If fine-grained measurement data is distributed, then accurate network control is improved, but network overhead increases and efficiency decreases
Solution Approach 1:
The patent applies local quality by providing different levels of measurement data detail to different network entities or for different network conditions. Instead of uniformly distributing fine-grained data across the entire network, the system selectively provides detailed measurements only where necessary, maintaining accurate local control while improving overall network efficiency by reducing unnecessary data distribution.
Data Source
AI summary
The present disclosure relates to a computer implemented method, performed by a wireless device, for reducing data transmission in a communications network by compression of measurements of network characteristics of the communications network, comprising the method steps of: obtaining a trained encoder, of a trained autoencoder, performing a measurements of network characteristics of the communications network, applying the trained encoder to compress the result of the measurements of network characteristics, and transmitting the compressed representation of measurements of network characteristics towards a network entity, whereby the network entity may perform a method comprising the method steps of: obtaining a trained decoder, of the trained autoencoder, receiving a compressed representation of a measurements of network characteristics, and applying the trained decoder to reconstruct the compressed representation of the measurements of network characteristics.