Efficient productivity prediction model based on edge data compression in smart farms
Amid escalating global farmland degradation alongside rising food demand. Smart farms are playing an increasingly vital role as a key approach to enhancing crop productivity. By integrating Internet of Things (IoT) devices with edge computing, smart farms significantly improve real-time data process...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | Smart Agricultural Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772375525004733 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Amid escalating global farmland degradation alongside rising food demand. Smart farms are playing an increasingly vital role as a key approach to enhancing crop productivity. By integrating Internet of Things (IoT) devices with edge computing, smart farms significantly improve real-time data processing and decision-making capabilities, thereby enhancing agricultural productivity. However, existing smart farms often face challenges, such as inefficiencies and performance bottlenecks, due to the limitations of traditional cloud computing architectures. For providing solutions to the problems existing in current smart farms, such as excessive energy consumption, and redundant data transmission, this paper proposes an adaptive optimization strategy based on priority scheduling and multi-source information fusion. This strategy integrates lightweight edge models and region-aware clippings and compression techniques to reduce data transmission while retaining key agronomic features. Furthermore, the strategy's multi-dimensional resource-aware scheduling and optimized network multiplexing significantly enhance the efficiency of data acquisition and transmission. Meanwhile, a cloud-edge collaborative decision-making model is adopted to accurately analyze crop maturity through real-time processing of heterogeneous data. Experimental results show that under minimal packet loss, the system significantly improves data transmission performance and reasoning reliability. Even under high compression conditions, the precision loss remains at a relatively low level. This study effectively balances data efficiency and analytical precision through advanced edge intelligence, showcasing its feasibility and application potential in resource-constrained agricultural settings. The proposed approach offers a novel solution for precision agriculture, contributing to global food security and sustainable development. |
|---|---|
| ISSN: | 2772-3755 |