Water Related

Sustainability and Productivity Enhancement IoT system for Agriculture

AP064

Minh-An DAO (The University of Melbourne, Victoria 3010 Australia)

Apr 02, 2022 3293 views

Sustainability and Productivity Enhancement IoT system for Agriculture

The project vision is to create a modulo IoT network that could be easily modified and applied onto various types of farms and greenhouses to help optimize water use, give insights, and impact the health of crops and the surrounding environment. Hence, increase the quality of the product going to the market and reduce the wastes that will contribute to long-term sustainability.
An IoT network will include a master node made of the FPGA Cloud Connectivity Kit, which will be responsible for collecting data from the sensor nodes, communicating with the cloud along with controlling the actuators that will affect a specific crop on the field.
Each Sensor Node will have its own MCU connected with a Soil Moisture and pH Measurement sensor (CN0398), a Volatile Organic Compound (VOC) Detector (CN0395), the Light Recognition System (CN0397), and potentially any other sensors that the customer requests. The data collected from these sensors will be transmitted to the Master node through wired RS485, wireless LoRa, LoRaWAN or other local transmitting methods (depends on specific setup). The moisture data collected will be used to control a watering pump through an isolated Contactor. pH or other soil qualities data can be statistically displayed to give the user insight into what should be adjusted to the fertilizer. Moreover, the VOC and Light data can be used to conditioning airflow in the greenhouse and changing lighting components to provide the best environment for the crops to thrive.
The cloud-based service will be in contact with the master node to connect the user from anywhere around the world to monitoring and controlling their farm. Besides, the cloud is also responsible for updating the system's firmware Over-The-Air (OTA) and store the processed data from the FPGA for further analysis and future improvement.
If time permits, edge computing Machine Learning will also be applied to the master node to automatically control the watering, lighting and air ventilating based on the crop that is being monitored, hence reduce the network bandwidth, contribute to the long-term energy efficiency compared to applications that do most calculating on the cloud. This network can be scaled up with many Master Nodes, each responsible for specific crops in a greenhouse or a farm, connected all together and monitored by the cloud or by a local Grant Master Node. We are expected to test the system on a greenhouse facility in Vietnam after finishing the prototype, which will give us a better insight into how the system operates.
Through the project, besides expecting to learn a heap of new useful knowledge, our team hopes to create a foundation for improving the efficiency of watering and energy usage in agriculture, especially in developing countries such as our hometown Vietnam.

Project Proposal


1. High-level project introduction and performance expectation

The project vision is to create a modulo IoT network that could be easily modified and applied to various types of farms and greenhouses to help optimize water use, give insights, and impact the health of crops and the surrounding environment. Hence, increasing the quality of the product going to the market and reducing the waste that will contribute to long-term sustainability.

An IoT network will include a master node made of the FPGA Cloud Connectivity Kit, which will be responsible for collecting data from the sensor nodes, communicating with the cloud, and controlling the actuators that will affect a specific crop on the field.

Each Sensor Node will have its own MCU connected with a temperature sensor, a soil moisture sensor, a Volatile Organic Compound (VOC) Detector (CN0395) and potentially any other sensors that the customer requests. The data collected from these sensors will be transmitted to the Master node through wired RS485, wireless LoRa, LoRaWAN or other local transmitting methods (depending on the specific setup). All the sensor data can be statistically displayed on the webserver to give the user insight into what should be adjusted. The moisture data collected will be used to control a watering pump through an isolated relay (stimulating a contactor for a high current pump). Moreover, the VOC data can be used to condition airflow in the greenhouse to provide the best environment for the crops to thrive.

The cloud-based service will be in contact with the master node to connect the user from anywhere around the world to monitor and control their farm. Besides, the cloud could also be responsible for updating the system's firmware Over-The-Air (OTA) and storing the processed data from the FPGA for further analysis and future improvement.

If time permits, edge computing Machine Learning will also be applied to the master node to automatically control the watering, lighting and air ventilating based on the crop that is being monitored, hence reducing the network bandwidth, contribute to the long-term energy efficiency compared to applications that do most calculating on the cloud. This network can be scaled up with many Master Nodes, each responsible for specific crops in a greenhouse or a farm, connected all together and monitored by the cloud or by a local Grant Master Node.

Besides expecting to learn new useful knowledge through the project, our team hopes to create a foundation for improving the efficiency of watering and energy usage in agriculture, especially in developing countries.

2. Block Diagram

3. Expected sustainability results, projected resource savings

Expected sustainability

- Improving the efficiency of watering and energy usage. Hence saving water and energy.

- Remote monitoring of the greenhouse condition lead to sufficient management of the resources.

 

Expected outcome:

- Learn new helpful knowledge.

- Proof of concept that all the sensor data can be collected and monitored remotely.

- Proof of concept that actuators can be controlled remotely through the web interface.

- Proof of concept that the system can be updated and managed remotely (OTA - Over The Air).

4. Design Introduction

The purpose of the design is to create an embedded system that has the ability to adapt and adjust its functionalities based on the requirements of the field, serving the purpose of monitoring and impacting the environment variables in agriculture. To successfully address this, the DE10-Nano FPGA  play a crucial role as the configurable brain. Each system can be deployed to an independent farm or agriculture area, and the Azure IoT Hub acts as a management tool for controlling a pool of active systems.

The master node includes the DE10-Nano, the RFS board for WiFi connectivity option (or the Ethernet port on DE10-Nano can be utilized), and an addon board on top of the RFS to serve as a connection hub to the slave nodes.

Master node block diagram

 

 

The slave node includes an MCU responsible for collecting sensor data and communicating with the master node

Communication between the master node and the slave node can be varied based on the need and current farm setup. For this proof of concept, we use RS485 as the medium since it has been widely known and used in practice for a long time.

A DE10-Nano FPGA at the brain of the master node brings the power of volatility to the setup, since it can be easily configured to work with almost any kind of communication method, and even become a sensor node itself by just changing the supporting daughter boards to fit a specific configuration.

 

 

 

5. Functional description and implementation

Master node:

Addon board design

Complete master node setup

Slave node:

Design

Implementation

 

Inter-connection between 1 Master node and 2 Sensor nodes:

For the proof of concept, we utilize 1 master node with 2 sensor nodes. But since we are using RS485, many more sensor nodes can be connected to 1 master. And thanks to the Azure cloud, a system of many master nodes can be controlled, update and manage remotely.

Web interfaces:

 

 

6. Performance metrics, performance to expectation

The cloud provided by Microsoft Azure fills in the gap for IoT edge large-scale deployment, where all the FPGA master nodes can be remotely controlled and manage which version and which type of software are being installed without the need to be physically in contact with the master nodes. Hence, the proof of concept of update OTA (Over The Air) is provided almost immediately when combining Intel FPGA with Microsoft Azure IoT Hub.

The Master node has been configured to contain 02 Nios II cores (an MCU inside the FPGA), one responsible for the communication with the RS485 through UARTs, and the other responsible for collecting data from sensors attached to itself. However, due to time limitations, we haven't been able to finish the connection between the communication Nios II core to the HPS on the DE10-Nano to finish a complete application. However, this still shows a proof of concept that the sensor data can be collected, both from the slave nodes and from within the master node itself. This proof illustrates the potential of an Intel FPGA in projects where the volatility in changing the hardware setup and edge computing is needed, which can create a massive barrier for conventional SoCs.

 

7. Sustainability results, resource savings achieved

With the advantage of easily modifying and configuring to fit many hardware requirements, on top of the ability to implement hardware edge computing on an embedded device, it is clear to see the sustainability results if the Intel FPGA is applied to the future agriculture industry, where resources such as water, energy, fertilizer, ... can be optimized to extract the most value in the shortest amount of time. From that foundation, reduce waste and slowly release the bad footprint that humans leave on the earth.

8. Conclusion

In conclusion, after the journey through this project, we realize the potential of further optimizing water and energy usage with the help of configurable hardware that conventional ones cannot possess. Even though we haven't been able to complete a fully functional system within the time frame of the contest, the proof of concepts we achieved is promising for future developments.

0 Comments



Please login to post a comment.