Mesh Network Transmission Power Control Using Supervised Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Wireless mesh networks in IoT deployments face inefficiencies due to fixed maximum transmission power thresholds, leading to unnecessary energy consumption and interference with neighboring nodes, as they often use higher power than needed for successful packet transmission.
Innovation Solution
Implementing supervised and semi-supervised learning to dynamically adjust transmission power thresholds based on real-time network conditions, using metrics like expected transmission count, latency, and signal strength, to determine minimum power requirements for maintaining connectivity and throughput.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If mesh network nodes use maximum transmission power threshold for all communications, then communication reliability is improved, but energy consumption increases unnecessarily
Solution Approach 1:
The patent implements dynamic transmission power adjustment where nodes continuously monitor packet delivery success rates and adaptively modify their transmission power thresholds. Instead of using fixed maximum power, the system dynamically scales power levels based on real-time network conditions and individual node performance, resolving the contradiction between maintaining reliable communication and reducing unnecessary energy consumption.
Solution Approach 2:
The system changes the transmission power parameter based on observed communication outcomes. Nodes adjust their power thresholds upward when packet delivery fails and downward when delivery succeeds, creating an adaptive parameter adjustment mechanism that optimizes the balance between communication reliability and energy efficiency.
2Reliability
If mesh network nodes use maximum transmission power threshold, then packet delivery success is improved, but interference with neighboring nodes increases
Solution Approach 1:
The patent enables each mesh node to independently adjust its transmission power threshold based on its local communication conditions and packet delivery performance. This localized adaptation allows nodes to use minimum necessary power for their specific needs, reducing overall network interference while maintaining individual packet delivery success rates.
Solution Approach 2:
The system implements dynamic power threshold adjustment where nodes monitor their own packet delivery success and adaptively modify transmission power. This dynamic approach ensures nodes use only the power necessary for successful communication, preventing excessive interference to neighboring nodes while maintaining reliable packet delivery.
3Device complexity
If fixed maximum transmission power is used, then implementation simplicity is maintained, but adaptability to changing network conditions deteriorates
Solution Approach 1:
The patent implements a self-service mechanism where mesh nodes automatically monitor their own packet delivery success rates and autonomously adjust their transmission power thresholds without external intervention. This self-adjusting capability provides adaptability to changing network conditions while maintaining implementation simplicity, as the adaptation logic is embedded in standard node operations.
Data Source
AI summary
In one embodiment, a technique for dynamic transmission power in wireless mesh networks using supervised and semi-supervised learning is provided. A first device of a mesh communication network may receive a set of transmission power metrics indicative of network conditions between a second device of the mesh communication network and a plurality of child nodes associated with the second device. The first device may provide the set of transmission power metrics as input to a supervised machine learning process that probabilistically determines one or more minimum transmission power thresholds for nodes of the mesh communication network. The first device may obtain an output from the supervised machine learning process comprising an indication of a particular minimum transmission power threshold for the second device. The first device may control the second device to exchange packets with the plurality of child nodes using the particular minimum transmission power threshold.