Network Objectives Management for Cognitive Radio Access
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cognitive network management (CNM) systems face challenges in automatically setting and managing conflicting key performance indicators (KPIs) across different sub-networks, requiring manual intervention and lacking efficient mechanisms for translating high-level operator goals into specific network actions.
Innovation Solution
The introduction of a Sub-Network Objective Translator (SNOT) that automates the translation of operator objectives into specific KPI targets for cognitive functions, using a framework with components like Network Objectives Manager, Environment Modelling & Abstraction, Configuration Management Engine, Decision & Action Engine, and Coordination Engine to manage and coordinate network configurations and actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If manual target setting for cognitive functions is performed, then flexibility and adaptability to changing environments are improved, but system complexity and operational burden increase
Solution Approach 1:
The cognitive function is designed to automatically determine its own targets based on observed network states and performance metrics. The function monitors network conditions, identifies optimization opportunities, and sets appropriate targets without external intervention, enabling self-configuration and self-optimization capabilities that adapt to changing environments while reducing operational complexity
Solution Approach 2:
The system implements continuous feedback loops where the cognitive function observes network performance, evaluates the impact of its actions, and adjusts targets accordingly. This feedback mechanism enables automatic adaptation to changing network conditions while maintaining manageable system complexity through closed-loop control
2Ease of operation
If automated target setting is implemented, then operational burden is reduced, but ability to handle conflicting objectives and translate high-level goals into specific actions deteriorates
Solution Approach 1:
The target setting process is segmented into distinct cognitive stages: observation of network states, interpretation of performance metrics, identification of optimization opportunities, determination of specific targets, and evaluation of conflicting objectives. This segmentation allows the cognitive function to systematically handle complex target management while reducing operational burden through automated decomposition of high-level goals into actionable targets
Solution Approach 2:
The cognitive function dynamically adjusts target parameters based on observed network conditions and performance metrics. By changing target values and priorities according to real-time network state, the system automatically resolves conflicts between competing objectives and translates high-level operator goals into context-appropriate specific targets without manual intervention
3Adaptability or versatility
If cognitive functions independently learn optimal behavior, then adaptability to specific environments is improved, but coordination among multiple functions and conflict resolution deteriorates
Solution Approach 1:
Multiple cognitive functions are merged into a coordinated system where they share common observation capabilities and communicate through standardized interfaces. The cognitive functions collectively observe network states, share learned insights, and coordinate their target-setting activities, enabling environment-specific optimization while managing coordination complexity through systematic integration
Solution Approach 2:
An intermediary coordination mechanism is introduced that mediates between independently learning cognitive functions. This intermediary facilitates communication, resolves conflicts between competing targets, and ensures that environment-specific optimizations by individual functions do not negatively impact overall network performance, maintaining system-wide coherence
Data Source
AI summary
There are provided measures for network objectives management. Such measures for enabling network objectives management in radio access networks exemplarily comprise receiving a key performance indicator optimization input indicative of a key performance indicator and an optimization direction of said key performance indicator, deriving at least one key performance indicator entry based on said key performance indicator optimization input, said at least one key performance indicator entry comprising at least said optimization direction of said key performance indicator and prioritized target values for said key performance indicator, storing said at least one key performance indicator entry, deciding, for a cognitive function, a target value for said key performance indicator of said prioritized target values for said key performance indicator expected to be achieved by said cognitive function, and providing said decided target value for said key performance indicator and said optimization direction of said key performance indicator to said cognitive function.