Virtualized RAN Analytics for Cross-Layer Cell Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing radio access networks (RANs) face challenges in real-time analytics due to standardized data aggregation protocols that limit the sharing of data between network nodes, leading to inefficiencies in detecting and addressing network conditions such as sleeping cells, high received signal strength indicator (RSSI) issues, poor cell coverage, MIMO inefficiencies, PDCCH congestion, scheduler inefficiencies, neighbor cell interference, and protocol inefficiencies.
Innovation Solution
Implementing an analytics engine in a virtualized RAN that correlates time series of real-time metrics across multiple protocol layers to detect network conditions and modify configurations accordingly, utilizing codelets and execution environments to collect and analyze data in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If standardized data aggregation protocols are used for data sharing between network nodes, then interoperability is improved, but data sharing efficiency deteriorates
Solution Approach 1:
The patent segments network data into different types (performance data, configuration data, fault data) and processes them through specialized processing pipelines rather than using a single standardized aggregation protocol. This allows efficient handling of each data type while maintaining interoperability through standardized interfaces.
Solution Approach 2:
The patent introduces an analytics engine as an intermediary component that receives data from multiple network nodes, processes it according to specific analytics requirements, and generates insights. This intermediary layer enables efficient data sharing while maintaining compatibility with standardized protocols through its interfaces.
2Measurement precision
If real-time analytics are implemented across multiple protocol layers, then network condition detection accuracy is improved, but system complexity increases
Solution Approach 1:
The patent divides the analytics system into multiple processing pipelines, each dedicated to specific network conditions (e.g., one pipeline for detecting sleeping cells, another for high RSSI issues). Each pipeline processes data from specific protocol layers relevant to its detection goal, reducing overall system complexity while maintaining high detection accuracy.
Solution Approach 2:
The patent correlates time series data from multiple protocol layers (PHY layer, MAC layer, RLC layer, PDCP layer) across different dimensions to detect network conditions. By analyzing data across these multiple dimensions simultaneously, the system achieves high detection accuracy without requiring a single overly complex analysis mechanism.
3Reliability
If dedicated processing hardware is deployed for each base station, then processing reliability is improved, but deployment cost increases
Solution Approach 1:
The patent implements a universal analytics engine that can process data from multiple network nodes and perform various analytics functions (detecting different network conditions, generating different types of insights). This single multi-functional platform replaces the need for dedicated processing hardware at each base station, reducing deployment costs while maintaining reliability through centralized robust processing.
4Adaptability or versatility
If virtualized RAN with generic computing resources is used, then scalability is improved, but processing performance deteriorates
Solution Approach 1:
The patent pre-configures multiple processing pipelines with specific detection algorithms and data sources assigned to each pipeline. This preliminary organization allows the virtualized system to efficiently process data without the overhead of dynamic resource allocation, maintaining high processing performance while benefiting from the scalability of generic computing resources.
Data Source
AI summary
Described are examples for providing radio access network (RAN) analytics for a virtualized base station. An analytics engine includes a memory storing one or more parameters or instructions for operating the virtualized RAN and at least one processor coupled to the memory. The analytics engine is configured to perform multiple protocol layers of RAN processing for at least one cell at the virtualized base station. The analytics engine is configured to determine a time series of real-time metrics at two or more layers of the multiple protocol layers for the at least one cell or a user equipment (UE) connected to the at least one cell. The analytics engine is configured to correlate a time series for each of the two or more layers to detect a network condition. The analytics engine is configured to modify a configuration of the at least one cell based on the detected network condition.