# Leveraging IoT Solutions for Real-Time Data Acquisition - Savonia AMK

> Time series data is an essential component in various fields including finance, economics, energy and environment.

## Introduction
Time series data is an essential component in various fields including finance, economics, energy, environment and many more. Large collections of diverse data acquired over long periods of time can be used to create valuable information, which in turn can be converted to usable knowledge to form a basis for decision making. In recent times, artificial intelligence (AI) has become a viable means to extract such knowledge from seemingly meaningless numbers and other symbols.

## Defining IoT and IIoT
The Internet of Things (IoT) refers to devices connected to the Internet. In industrial contexts, the term Industrial IoT (IIoT) is used to describe Internet-connected devices that humans do not directly interact with. These systems operate automatically, without human intervention, typically consisting of sensors connected to a data ingestion and storage service via an "edge" device.

## The ÄLLITÄ Project Implementation
During the ÄLLITÄ project, IoT devices were installed on Savonia campuses in Varkaus and Kuopio to develop AI solutions for optimizing energy consumption in public buildings. The system monitors parameters such as building occupancy and local weather conditions.

### Varkaus Campus Monitoring
*   **Occupancy (CO2):** Three custom systems using Sensirion SCD30 sensor modules and ESP32S3-based microcontrollers were deployed. Data is sent via WiFi to the Thingsboard data platform.
*   **Occupancy (Motion):** Six Milesight VS350 2-way PIR motion sensors were installed, using LoRaWAN technology to communicate with a Milesight UG65 gateway connected to the campus network.
*   **Weather:** A Vaisala WXT520 weather station and a custom pyranometer setup (Kipp&Zonen CMP3, Phoenix Contact MACX-MCR, and LiuDr SDI12/ADC) are connected to a Raspberry Pi 3B+ to relay data to the platform.

### Microkatu Campus Monitoring
Two Raspberry Pi devices are connected to the campus 5G testing infrastructure to monitor 5G signal quality parameters, which are then sent to the on-premises database.

## Data Analysis and AI Integration
Data analysis and AI model development are performed on an NVIDIA DGX computing platform located in the on-premises server environment. The system uses REST API calls to fetch historical data for model training and real-time data for inference in AI-powered applications.

## Considerations for IoT Management
As the number and variety of devices increase, low-level data management can become complex. A well-defined, flexible data backend is essential, as is careful planning of the procurement and integration process to ensure scalability and system stability.

## Authors
*   **Mika Leskinen**, RDI Specialist, DigiCenter, Savonia University of Applied Sciences, mika.leskinen@savonia.fi
*   **Shahbaz Baig**, RDI Specialist, DigiCenter, Savonia University of Applied Sciences, shahbaz.baig@savonia.fi
*   **Premton Canamusa**, RDI Specialist, DigiCenter, Savonia University of Applied Sciences, premton.canamusa@savonia.fi
*   **Aki Happonen**, Digital Development Manager, DigiCenter, Savonia University of Applied Sciences, aki.happonen@savonia.fi
*   **Laura Leppänen**, RDI Specialist, Savonia University of Applied Sciences, laura.leppanen@savonia.fi