Cognitive Network Optimization via Quality Indicators
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cognitive network management systems face challenges in coordinating multiple self-organizing network functions across different vendors, leading to nondeterministic environments and difficulties in managing learning behaviors, especially in multi-vendor scenarios, where standardization efforts are complex and intellectual property is protected, making it hard to exchange information on the effects of cognitive functions' actions on other networks.
Innovation Solution
A distributed approach using a Cognitive Function Action Quality Indicator (CFAQI) on a pre-defined scale allows vendors to quantify and communicate the effects of their actions on other functions without requiring inter-vendor agreement, enabling each CF to compute and share a generic quality measure across standardized interfaces, thereby facilitating coordinated network optimization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If cognitive functions learn and adapt automatically to optimize network parameters, then network optimization flexibility and adaptability improve, but coordination complexity between multiple functions increases
Solution Approach 1:
A coordinator function is introduced as an intermediary component that manages communication and coordination between multiple cognitive functions. The coordinator receives actions from cognitive functions, determines affected functions, and facilitates information exchange through standardized interfaces, thereby reducing direct coordination complexity between individual cognitive functions.
Solution Approach 2:
The coordination task is segmented into manageable components: action identification, effect determination, and standardized interface communication. Each cognitive function operates independently but connects through defined interfaces with the coordinator, allowing modular management of complexity.
2Measurement precision
If detailed inter-vendor coordination rules are implemented to manage learning behaviors, then coordination precision improves, but synchronization effort and complexity increase
Solution Approach 1:
The system changes the parameter of coordination from detailed vendor-specific rules to a standardized quality indicator scale. Instead of requiring precise alignment of multiple coordination parameters, the system uses a simplified scale (e.g., -5 to +5) that captures the essence of coordination needs without requiring complex synchronization protocols.
Solution Approach 2:
The coordinator uses disposable, standardized quality indicators rather than maintaining complex, persistent coordination state between vendors. The quality indicator serves as a lightweight communication mechanism that can be exchanged without requiring long-term synchronization agreements.
3Productivity
If vendors share detailed measurement data and KPI definitions to improve coordination, then coordination effectiveness improves, but intellectual property protection and information security worsen
Solution Approach 1:
The system extracts only the essential coordination information from detailed KPI measurements and transforms it into a standardized quality indicator. This extraction process removes vendor-specific details and proprietary algorithms while retaining the core coordination meaning, allowing sharing without intellectual property exposure.
Solution Approach 2:
Instead of sharing original KPI definitions and measurement data, the system creates a copy in the form of standardized quality indicators. This copy preserves the coordination information in a vendor-neutral format that can be exchanged without revealing underlying proprietary mechanisms.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
There are provided measures for coordinated network optimization by cognitive network management. Such measures exemplarily comprise initiating a configuration action, wherein said configuration action comprises a change of at least one network related configuration parameter, receiving, from at least one of said plurality of control entities, a respective quality indicator, wherein each of said received quality indicators is indicative of an interpretation of effects of said configuration action on said respective one of said at least one of said plurality of control entities mapped into a predetermined quality indicator range, and evaluating said configuration action based on each of said received quality indicators.