In testing the system, we want to test how the sensor responds to different distances of objects and how the traffic light LEDs light up accordingly. The steps are set out here:
Place an object in front of the ultrasonic distance sensor.
Observe the traffic light LEDs and the servo motor.
Move the object closer to the sensor (less than 100 cm). Notice the red, yellow, and green LEDs’ turn-on sequence and that the servo motor moves to the 0-degree position.
Move the object further away from the sensor (more than 100 cm). Notice again the LEDs turn on in different sequences, and the servo motor moves to the 90-degree position.
In this practical, we have created a smart traffic control system using an ESP32 microcontroller. The ultrasonic distance sensor represents the presence of vehicles at an intersection. When the distance to the nearest vehicle is greater than 100 cm, the system optimizes the traffic flow by changing the traffic light to yellow and green in sequence and adjusting the position of the servo motor, simulating the opening of a gate. When the distance is less than 100 cm, the traffic light turns red, then yellow in sequence, and the servo motor moves to the closed position.
You can also explore the following to further build on this practical:
Multiple intersections: Extend the system to manage multiple intersections by connecting additional ultrasonic distance sensors, servo motors, and traffic light LEDs. This would allow you to explore the coordination and optimization of traffic flow across a network of intersections, simulating a more realistic traffic management system.
Vehicle detection: Replace the ultrasonic distance sensor with a camera module and integrate ML algorithms for vehicle detection and classification. This would enable the system to detect different types of vehicles (for example, cars, trucks, and bicycles) and adjust the traffic light duration accordingly, optimizing traffic flow based on vehicle type and density.
By utilizing edge computing, this system can process the sensor data locally and make decisions in real time, without the need for constant communication with a central server. This practical demonstrates how IoT benefits from edge networks, how edge networks are designed, and considerations made in optimizing them. Additionally, it shows how to architect simple edge deployments using an Arduino-based IoT device.
Summary
In this chapter, we learned the fundamentals of edge computing and discussed the benefits that can be derived from it. Although it certainly requires more understanding of its setup and has its own set of challenges based on the decentralized network it needs to abide by, it provides a cost-effective way for large workloads to be performed while ensuring that they do not get congested when they are directed toward a centralized hub, as with most solutions. We looked at an exercise where an edge device in the form of an ESP32 device was built to retrieve information from a DHT11 sensor and used for both obtaining data and running an ML model on it, seeing how powerful edge computing can be. Toward the end, we also did a practical on creating a simple network for edge computing and further learned about strategies that can be used to optimize edge networks, evaluate them, and make appropriate design decisions based on them, while also applying the knowledge that we have learned so far to a case study based on how edge computing would be set up for a smart city.
Having navigated through this chapter, readers have not only acquired foundational knowledge about edge computing but also gleaned practical insights from hands-on exercises. This understanding equips them with the skills to discern the unique advantages and potential challenges posed by decentralized networks.
In the next chapter, we will be looking at how we can utilize cloud computing based on Amazon Web Services (AWS) to further strengthen our workloads and make the most of the capabilities that it has to offer for building IoT networks.
Further reading
For more information about what was covered in this chapter, please refer to the following links:
More of an understanding of fog computing: https://www.heavy.ai/technical-glossary/fog-computing
Learn more about TensorFlow: https://www.tensorflow.org/learn
Explore more on edge computing in smart cities: https://stormagic.com/company/blog/edge-computing-for-iot-based-energy-management-in-smart-cities
Understand a case of detecting cryptocurrency mining threats with AWS: https://aws.amazon.com/blogs/iot/detect-cryptocurrency-mining-threats-on-edge-devices-using-aws-iot/
Look at more case studies of edge computing solutions: https://www.nec.com/en/global/techrep/journal/g17/n01/170106.html
Leave a Reply