Scholarlink

<p>Smart building can play a crucial role in optimizing energy consumption and overall efficiency. In this research we present a smart building system specifically designed for educational institutions to improve energy efficiency and durability. The system integrates an STM32 microcontroller, a three-phase energy meter, Long Range Wide Area Network (LoRaWAN) connectivity and The Thing Network (TTN) cloud. A key innovation is the use of Deep Q-Network (DQN), a machine learning algorithm that automates the complex task of analyzing energy consumption patterns in laboratories and classrooms which eliminates the need of installing traditional observation methods. Energy monitoring in educational institutions are undergoing a significant transformation with the integration of LoRaWAN and TTN which results in significant energy savings. The systems notable features include the ability to independently measure the energy consumption of 60 computers, 80 LED lights and 75 fans located throughout the building. Our work proves that the energy management and load balancing can be achieved using an intelligent meter coupled with an STM32 microcontroller with the TTN and the facility manager can gain real time insight into how energy is used, enabling them to optimize their energy usage. The implementation of this LoRaWAN based system results in 23% reduction of overall energy consumption over six months which highlights the effectiveness of promoting sustainable energy practices within the educational settings. This research addresses challenges related to diverse data scenarios and scaling limitations by promoting a sustainable and smart learning environment.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhanced energy efficiency smart buildings through LoRaWAN and adaptive machine learning techniques

  • 期刊论文

  • 发表日期：

    2025年2月14日

查看全文
  • Kothandam Thirunavukkarasu,
  • Leo Raju

摘要

Smart building can play a crucial role in optimizing energy consumption and overall efficiency. In this research we present a smart building system specifically designed for educational institutions to improve energy efficiency and durability. The system integrates an STM32 microcontroller, a three-phase energy meter, Long Range Wide Area Network (LoRaWAN) connectivity and The Thing Network (TTN) cloud. A key innovation is the use of Deep Q-Network (DQN), a machine learning algorithm that automates the complex task of analyzing energy consumption patterns in laboratories and classrooms which eliminates the need of installing traditional observation methods. Energy monitoring in educational institutions are undergoing a significant transformation with the integration of LoRaWAN and TTN which results in significant energy savings. The systems notable features include the ability to independently measure the energy consumption of 60 computers, 80 LED lights and 75 fans located throughout the building. Our work proves that the energy management and load balancing can be achieved using an intelligent meter coupled with an STM32 microcontroller with the TTN and the facility manager can gain real time insight into how energy is used, enabling them to optimize their energy usage. The implementation of this LoRaWAN based system results in 23% reduction of overall energy consumption over six months which highlights the effectiveness of promoting sustainable energy practices within the educational settings. This research addresses challenges related to diverse data scenarios and scaling limitations by promoting a sustainable and smart learning environment.