Deploying an energy efficient, secure & high-speed sidechain-based TinyML model for soil quality monitoring and management in agriculture

Abstract

This paper presents an innovative deployment strategy for a power-aware and delay-aware TinyML model optimized for agricultural soil quality monitoring and management. The proposed method employs an enhanced fusion of Dynamic Voltage and Frequency Scaling (DVFS), Sleep/Wake Strategies based on Genetic Algorithms, Energy Harvesting, and Task Partitioning. Through this method, the model reduces energy consumption by 8.5% and delay by 10.4%, while maintaining accuracy comparable to state-of-the-art techniques such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Q Learning techniques. The proposed model also uses a Proof-of-Energy Efficiency (PoEE) based consensus for creation of new blocks. These blocks are added to different sidechains for strengthening the security levels. While blockchains require higher energy during mining, the proposed PoEE Model uses a light weight consensus, which is backed by Q Learning based sidechain formation process. This lightweighted combination allows the model to reduce delay, maintain lower energy consumption, with better communication throughput even under multiple attack scenarios. This model is necessary due to the growing demand for sustainable and accurate agricultural practices. The quality of the soil is crucial to soil yield and productivity. Monitoring and managing soil conditions enables farmers to optimize irrigation, fertilization, and overall resource allocation, leading to an increase in soil yield and a decrease in environmental impacts. However, the deployment of energy-efficient and low-latency TinyML models is essential to enable real-time decision-making in agricultural settings with limited resources. This power-aware and delay-aware TinyML model has applications in various agricultural real-time scenarios. It can be used to continuously monitor soil quality parameters including moisture content, pH level, and nutrient levels for various farm types. Incorporating sensors and low-power microcontrollers, the model enables on-site analysis and timely farmer feedbacks. The decreased energy consumption extends the battery life of deployed devices, whereas the decreased delay ensures that soil management interventions and treatments are responsive and timely for different scenarios.