Context-Aware Collaborative Intelligence With Spatio-Temporal In-Sensor-Analytics for Efficient Communication in a Large-Area IoT Testbed

• Published in: IEEE internet of things journal 2021-04, Vol.8 (8), p.6800-6814
• Main Authors: Chatterjee, Baibhab, Seo, Dong-Hyun, Chakraborty, Shramana, Avlani, Shitij, Jiang, Xiaofan, Zhang, Heng, Abdallah, Mustafa, Raghunathan, Nithin, Mousoulis, Charilaos, Shakouri, Ali, Bagchi, Saurabh, Peroulis, Dimitrios, Sen, Shreyas
• Format: Article
• Language: English
• Subjects: Algorithms; Ambient intelligence; Anomalies; Anomaly detection; Batteries; clustering; collaborative intelligence (CI); context awareness; Data compression; edge intelligence; Energy consumption; in-sensor analytics (ISA); Internet of Things; Leakage current; low power; smart agriculture; smart city; smart home; Switches; Temperature sensors; Wireless sensor networks; wireless sensor networks (WSNs)
• ISSN: 2327-4662; 2327-4662
• DOI: 10.1109/JIOT.2020.3036087

Decades of continuous scaling has reduced the energy of unit computing to virtually zero, while energy-efficient communication has remained the primary bottleneck in achieving fully energy-autonomous Internet-of-Things (IoT) nodes. This article presents and analyzes the tradeoffs between the energies required for communication and computation in a wireless sensor network, deployed in a mesh architecture over a 2400-acre university campus, and is targeted toward multisensor measurement of temperature, humidity and water nitrate concentration for smart agriculture. Several scenarios involving in-sensor analytics (ISA), collaborative intelligence (CI), and context-aware switching (CAS) of the cluster head during CI has been considered. A real-time co-optimization algorithm has been developed for minimizing the energy consumption in the network, hence maximizing the overall battery lifetime. Measurement results show that the proposed ISA consumes \approx 467\times lower energy as compared to traditional Bluetooth low energy (BLE) communication, and \approx 69500\times lower energy as compared with long-range (LoRa) communication. When the ISA is implemented in conjunction with LoRa, the lifetime of the node increases from a mere 4.3 h to 66.6 days with a 230-mAh coin cell battery, while preserving >99% of the total information. The CI and CAS algorithms help in extending the worst case node lifetime by an additional 50%, thereby exhibiting an overall network lifetime of \approx 104 days, which is >90% of the theoretical limits as posed by the leakage current present in the system, while effectively transferring information sampled every second. A Web-based monitoring system was developed to continuously archive the measured data, and for reporting real-time anomalies.