Two-Tier UAV Relay Networks for Reliable Smart Agriculture Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The lack of conventional communication infrastructure and inefficient data transfer due to unstable wireless connections in rural agriculture areas hinder the implementation of smart agriculture systems, where agriculture sensors struggle to directly communicate with remote cloud servers, and data transmission is unreliable and prone to buffer overflow.
Innovation Solution
A two-tier hybrid network architecture utilizing unmanned aerial vehicles (UAVs) to form dynamic networks, where agriculture sensors and UAVs use short-range communication, and UAVs and cloud servers use long-range communication, with multi-agent reinforcement learning (MARL) to optimize data delivery, employing the Focus Coordination Multi-Agent Deep Deterministic Policy Gradient (FC-MADDPG) algorithm for decentralized decision-making.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If agriculture sensors use short-range communication protocols to transfer data, then communication cost is reduced and ease of operation is improved, but communication range is limited and cannot reach remote cloud servers
Solution Approach 1:
The communication system is segmented into two tiers: first-tier short-range communication between sensors and UAVs, and second-tier long-range communication between UAVs and cloud servers. This segmentation allows each tier to use optimized communication protocols for its specific range and cost requirements.
Solution Approach 2:
UAVs serve as intermediary nodes that bridge the gap between agriculture sensors and remote cloud servers. The UAVs collect data from sensors using short-range communication and transmit it to cloud servers using long-range communication, eliminating the need for sensors to directly communicate over long distances.
2Reliability
If conventional communication infrastructure is built up in rural areas, then data transmission reliability is improved, but device complexity and cost increase
Solution Approach 1:
The system uses existing UAV technology and open wireless communication standards that can operate without dedicated infrastructure. The UAVs autonomously navigate and communicate using available resources, eliminating the need for complex dedicated communication infrastructure in rural areas.
Solution Approach 2:
The UAVs perform multiple functions: they act as data collection nodes, communication relays, and mobile routers. This multi-functionality replaces the need for separate dedicated communication infrastructure, reducing overall system complexity while maintaining reliability.
3Loss of information
If sensors continuously transfer data to avoid buffer overflow, then data loss is prevented, but transmission time increases and energy consumption rises
Solution Approach 1:
The system implements preliminary actions by having sensors buffer data locally and by pre-positioning UAVs in optimal locations for data collection. This allows sensors to accumulate data without immediate transmission, reducing transmission frequency and time while preventing buffer overflow through controlled local storage.
Solution Approach 2:
The system dynamically adjusts data transmission timing based on sensor buffer status and UAV availability. Transmission occurs only when necessary, optimizing the balance between preventing data loss and minimizing transmission time through adaptive, event-driven communication.
4Productivity
If multiple UAVs coordinate data delivery using centralized control, then routing optimization is improved, but system complexity and communication overhead increase
Solution Approach 1:
The control system is segmented into autonomous local decision-making at each UAV and decentralized coordination. Each UAV independently manages its own data collection and routing based on local observations, reducing the complexity of centralized control while maintaining overall system efficiency.
Solution Approach 2:
The system uses feedback mechanisms where UAVs continuously monitor network conditions, sensor data availability, and their own buffer status. This feedback enables autonomous routing decisions and dynamic adaptation to changing conditions without requiring complex centralized control.
Data Source
AI summary
An unmanned aerial vehicle (UAV) agent for forming a two-tier hybrid smart agriculture network architecture is provided. The UAV agent is configured to support two communication protocols, a short-range communication protocol and a long-range communication protocol. The agriculture sensor gathers agriculture data such as soil temperature and participates in a first-tier short range wireless communication network to send the collected data to at least one UAV agent. A UAV agent participates in one or more first-tier short-range communication networks to pick up sensor data from agriculture sensors in one or more clusters and also participates in a second-tier long-range communication network to route the collected sensor data to at least one cloud server. The tasks in both tier networks are formulated as optimization problems to achieve optimal data delivery and solved by using multi-agent reinforcement learning (MARL), which is implemented by the invented Focus Coordination Multi-Agent Deep Deterministic Policy Gradient (FC-MADDPG) algorithm.