UAV Selecting IoT Terminals via Deep Learning Auction for Smart Surveillance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In smart city environments with widespread Internet of Things (IoT) applications, existing surveillance systems using unmanned aerial vehicles (UAVs) face challenges in efficiently collecting and transmitting surveillance data due to limited wireless network coverage and constraints such as battery life and mobility of UAVs.
Innovation Solution
A smart surveillance system utilizing a UAV that selects IoT terminals using deep learning auction training to receive and transmit surveillance data through a network of base stations and the Internet, optimizing data collection based on distance and data similarity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If UAVs collect surveillance data from all IoT terminals in the coverage area, then the completeness of surveillance information is improved, but the energy consumption and operational time of UAVs deteriorate due to battery constraints
Solution Approach 1:
The system enables autonomous decision-making where the UAV independently selects which IoT terminals to surveil based on deep learning auction training that evaluates data redundancy and displacement factors, eliminating the need for manual intervention while optimizing energy usage
Solution Approach 2:
The system dynamically changes the selection parameters by using deep learning auction training that considers data redundancy and displacement factors, allowing the UAV to adaptively select terminals based on current operational conditions rather than fixed predetermined rules
2Loss of information
If UAVs transmit all collected surveillance data to terrestrial base stations, then the completeness of data analysis is improved, but the reliability of data transmission deteriorates when wireless network coverage is insufficient
Solution Approach 1:
The system extracts and processes critical surveillance data locally on the UAV using onboard deep learning auction training algorithms, separating essential data processing from centralized base station analysis to maintain operational reliability when network coverage is limited
Solution Approach 2:
The system segments the surveillance data collection and processing function into distributed autonomous UAV units that can independently evaluate and select terminals, rather than relying on centralized control, thereby maintaining functionality in areas with poor network coverage
3Productivity
If UAVs selectively collect surveillance data from specific IoT terminals, then the energy efficiency and operational time are improved, but the completeness of surveillance coverage deteriorates
Solution Approach 1:
The system implements feedback mechanisms where the deep learning auction training continuously evaluates data redundancy and displacement factors from previously collected surveillance data, allowing the UAV to adaptively adjust terminal selection decisions to maintain comprehensive coverage while optimizing energy efficiency
Data Source
AI summary
Provided is a smart surveillance system that includes one unmanned aerial vehicle (UAV), a plurality of Internet of Things (IoT) terminals distributed in a surveillance area, and a plurality of base stations distributed in the surveillance area, wherein the UAV selects any IoT terminal from among the plurality of IoT terminals using deep learning auction training, receives surveillance data from the selected IoT terminal, and transmits the surveillance data to a data center through the Internet and any one base station among the plurality of base stations.