A NODE AND NETWORK LEVEL SELF-RECOVERING DISTRIBUTED WIRELESS SENSOR ARCHITECTURE FOR REAL-TIME CROP MONITORING IN GREENHOUSES

Visual sensor networks (VSNs) have emerged as a new paradigm by giving sensors the capability to perceive and analyze their surroundings. Robust and fault-tolerant operations are crucial for non-contact plant monitoring systems in a greenhouse environment equipped with a VSN. Achieving such capabilities requires new methods to monitor system status and crop health, and automatically reconfigure for new functionalities due to dynamic changes in the greenhouse environment. New technologies, such as field-programmable gate arrays (FPGAs), provide hardware designers with the ability to create high-performance and adaptive solutions. In this study, a distributed wireless sensor architecture with self-recovery capability was designed and constructed. The experimental results showed that the test bed comprised of wirelessly connected FPGAs (Xilinx Virtex 5) was able to achieve node-level fault detection and recovery within 2.16 s and network level recovery in 5.39 s. The application of the proposed architecture in greenhouse-based plant production is a significant step toward building a robust system for monitoring plant status.