Walker Agent Actuator for IoT Sensor Coverage Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Low Power and Lossy Networks (LLNs) face challenges such as lossy links, low bandwidth, limited memory and processing capability, and changing environmental conditions, which complicate the optimization of relationships between connected objects in IoT networks, making it difficult to ensure optimal sensor coverage and resource management.
Innovation Solution
A walker agent is executed on actuators to adjust actuation settings based on sensor measurements, optimizing coverage by propagating through the network and leveraging machine learning to perform computations and adjust settings in a distributed manner, thereby optimizing sensor coverage without relying on centralized or remote resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If centralized or remote resources are used to optimize sensor coverage, then optimization capability is improved, but resource consumption and bandwidth usage increase
Solution Approach 1:
The walker agent enables actuators to autonomously optimize sensor coverage by executing optimization algorithms locally on the actuator itself. The actuator receives sensor measurements, computes optimal actuation settings through the walker agent, and adjusts its coverage area without requiring centralized control or remote resource allocation, thereby achieving self-service optimization that minimizes network bandwidth usage and resource consumption.
Solution Approach 2:
The optimization problem is segmented into individual actuator-level tasks rather than being solved centrally. The walker agent divides the global optimization problem into local sub-problems that each actuator solves independently based on its own sensor measurements and local context, reducing the overall computational burden on network resources while maintaining optimization effectiveness.
2Area of stationary object
If actuator settings are adjusted to improve sensor coverage, then coverage area is improved, but device complexity increases
Solution Approach 1:
The walker agent serves as an intermediary between sensor measurements and actuator control decisions. It receives raw sensor data, processes it through optimization algorithms, and generates simplified actuation settings that adjust the actuator's coverage area. This intermediary layer abstracts the complexity of coverage optimization, presenting a simple interface for area adjustment while handling the computational complexity internally.
3Productivity
If more processing is done locally on actuators to optimize coverage, then optimization efficiency is improved, but processing capability requirements increase
Solution Approach 1:
The walker agent implements partial action by performing only the necessary optimization computations locally on each actuator rather than requiring full-featured processing capabilities. It executes simplified optimization algorithms that achieve sufficient coverage improvement without demanding excessive processing power, accepting that local optimization may be less comprehensive than centralized optimization would provide.
Data Source
AI summary
In one embodiment, a first actuator in a network of sensors and actuators executes a walker agent configured to adjust an actuation setting of the first actuator. The actuation setting controls an area of coverage of the first actuator when actuated. The executing agent on the first actuator receives one or more sensor measurements from one or more of the sensors that are in communication range of the first actuator. The executing agent also controls, based on the received one or more sensor measurements, the area of coverage of the first actuator by adjusting its actuation setting, in an attempt to optimize coverage of the sensors in the network by the areas of coverage of the actuators. The first actuator unloads the executing walker agent after adjusting the actuation setting of the first actuator and propagates the agent to another one of the actuators in the network for execution.