Cognitive Network Multi-Layer Optimization via AI-Biased Pareto Fronts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cognitive networks are sub-optimized due to reactive single-parameter optimizations across non-adjacent protocol stack layers, leading to high latency and packet congestion, as they fail to coordinate the entire network performance effectively.
Innovation Solution
Implementing distributed Multi-Objective Optimization algorithms across multiple protocol stack layers using initialization parameters generated based on project or mission requirements, with convergence behaviors monitored to generate Pareto-Optimal solutions, and biased using AI to prioritize protocol stack layers, resulting in configuration parameters for optimal network resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If single-parameter optimization is applied across non-adjacent protocol stack layers, then optimization complexity is reduced, but overall network performance deteriorates due to lack of coordination
Solution Approach 1:
The patent segments the optimization process into multiple independent Multi-Objective Optimization (MOO) algorithms, each assigned to a specific protocol stack layer. Each MOO algorithm independently optimizes its layer while considering multiple parameters simultaneously, rather than using single-parameter optimization across layers. This segmentation maintains manageable complexity at each layer while achieving coordinated optimization across the entire network through the multi-objective nature of each algorithm.
Solution Approach 2:
The patent transitions from single-parameter optimization to multi-parameter optimization by introducing multiple objectives within each MOO algorithm. Instead of optimizing one parameter at a time across layers, each layer simultaneously optimizes multiple parameters (throughput, latency, packet loss, energy consumption) in parallel, adding a dimensional aspect to the optimization process that improves overall network performance while maintaining coordination.
2Reliability
If physical layer optimizes for high performing short distance links, then link quality is improved, but network latency increases due to large number of hops required
Solution Approach 1:
The patent introduces network layer routing optimization as an intermediary that coordinates with physical layer link optimization. The network layer MOO algorithm optimizes routing paths considering hop count and latency, while the physical layer MOO algorithm optimizes link quality. These two algorithms communicate and coordinate their decisions, allowing the system to achieve both high link quality and acceptable latency by selecting routes that balance both objectives rather than prioritizing link quality alone.
Solution Approach 2:
The patent dynamically changes optimization parameters across different protocol layers. The physical layer MOO algorithm adjusts link quality parameters (modulation, coding rate) based on channel conditions, while the network layer MOO algorithm adjusts routing parameters (hop count, path selection) based on overall network state. This parameter adaptation at multiple layers allows the system to respond to changing conditions and balance link quality against latency requirements.
3Ease of manufacture
If static relocation is used to move RF systems to new spectral bands, then spectrum allocation is simplified, but over-utilization of certain bands is exacerbated
Solution Approach 1:
The patent implements dynamic spectrum allocation through cognitive radio technology. Instead of static relocation to fixed spectral bands, the RF systems continuously sense the spectrum environment and dynamically select and switch between available frequency bands based on real-time conditions. This dynamic approach allows the system to adapt to spectrum availability, avoiding over-utilization of certain bands while maintaining simple operational procedures through automated spectrum management.
Solution Approach 2:
The cognitive RF systems perform self-service spectrum allocation by autonomously sensing the electromagnetic environment, identifying available frequency bands, and selecting appropriate channels without external intervention. This self-service capability enables balanced spectrum utilization across multiple bands, as each system independently adapts to local spectrum conditions and automatically relocates when bands become congested or unavailable.
Data Source
AI summary
System (300) and methods (400, 600) for providing a Cognitive Network (“CN”). The methods involve: partially solving Multi-Objective Optimization Algorithms (“MOOAs”) for Protocol Stack Layers (“PSLs”) using initialization parameters generated based on project requirements (572); and monitoring the convergence behaviors of MOOAs (584) to identify when solutions (106) thereof start to converge toward Pareto-Optimal solutions (104). In response to said identification, a convergence of a solution trajectory for at least one MOOA is “biased” so that compatible non-dominated solutions are generated at PSLs. A Pareto Front (100) for each PSL is determined by generating remaining solutions for MOOAs. The Pareto Fronts are analyzed in aggregate to develop Best Overall Network Solutions (“BONSs”). BONSs are ranked according to a pre-defined criteria. A Top Ranked Solution (“TRS”) is identified for BONSs that complies with current regulatory/project policies. Configuration parameters are computed for PSL protocols that enable implementation of TRS within CN.