Zabrina, Salsabila Aurellia (2026) Implementation of Model Predictive Control (MPC) in an IoT-Based Mini Greenhouse for Chili Plant Environment Control. Undergraduate thesis, UPN Veteran Jawa Timur.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Cover)
2208101007.-cover.pdf Download (1MB) |
|
Text (Bab 1)
22081010079.-bab1.pdf Download (224kB) |
|
Text (Bab 2)
22081010079.-bab2.pdf Restricted to Repository staff only until 17 July 2029. Download (649kB) |
|
Text (Bab 3)
22081010079.-bab3.pdf Restricted to Repository staff only until 17 July 2029. Download (840kB) |
|
Text (Bab 4)
22081010079.-bab4.pdf Restricted to Repository staff only until 17 July 2029. Download (2MB) |
|
Text (Bab 5)
22081010079.-bab5.pdf Download (202kB) |
|
Text (Daftar pustaka)
22081010079.-daftarpustaka.pdf Download (232kB) |
Abstract
Chili (Capsicum annuum L.) is a strategic horticultural commodity in Indonesia that is highly vulnerable to climate fluctuations and limitations in agricultural land availability. Conventional control systems such as On-Off switching, which are commonly used, are reactive in nature and inefficient in maintaining optimal microclimate stability. This research aims to design and build a smart IoT-based mini greenhouse prototype that implements a Model Predictive Control (MPC) algorithm to automatically regulate the microclimate and nutrition of chili plants. The system was built using an ESP32 microcontroller as the central processing unit, equipped with a DHT22 sensor (air temperature and humidity), a capacitive soil moisture sensor, an LDR light sensor, and a rain sensor as input devices. The actuators used include a DC fan, three water pumps, and LED growlight lamps. The MPC algorithm was implemented in an embedded manner on the ESP32 using a Multiple Input Single Output (MISO) model approach to control fan speed via PWM signals for stabilizing temperature and air humidity, as well as regulating the active duration of the main irrigation pump. Data monitoring and visualization are performed in real-time through a Next.js-based web dashboard connected to a VPS server, supplemented by critical condition notifications via a Telegram Bot. The development methodology used was Rapid Application Development (RAD). Test results indicate that the MPC algorithm successfully delivered adaptive and proactive actuation responses, significantly reducing extreme oscillations compared to conventional On-Off control systems, resulting in more efficient energy use. The IoT system successfully operated end-to-end with stable JSON telemetry data transmission to the API endpoint, an automatic nutrient scheduling module with Non-Volatile memory storage, and a Watchdog Timer-based fail-safe mechanism that ensures the overall reliability of the system.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | S Agriculture > S Agriculture (General) S Agriculture > SB Plant culture T Technology > TK Electrical engineering. Electronics Nuclear engineering T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5105 Computer Network T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5105.882 Internet |
||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Informatics | ||||||||||||
| Depositing User: | Ms. Salsabila Aurellia Zabrina | ||||||||||||
| Date Deposited: | 17 Jul 2026 06:52 | ||||||||||||
| Last Modified: | 17 Jul 2026 08:14 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/55767 |
Actions (login required)
 |
View Item |