Modeling and implementation of demand-side energy management system
Yazarlar (3)
Dr. Öğr. Üyesi Abdulkadir GÖZÜOĞLU
Tokat Gaziosmanpaşa Üniversitesi, Türkiye
Ondokuz Mayıs Üniversitesi, Türkiye
Ondokuz Mayıs Üniversitesi, Türkiye
| Makale Türü | Özgün Makale |
| Makale Alt Türü | ESCI dergilerinde yayınlanan tam makale |
| Dergi Adı | SIGMA JOURNAL OF ENGINEERING AND NATURAL SCIENCES-SIGMA MUHENDISLIK VE FEN BILIMLERI DERGISI |
| Dergi ISSN | 1304-7205 Wos Dergi Scopus Dergi |
| Dergi Tarandığı Indeksler | (ESCI) Mühendislik, Multidisipliner |
| Makale Dili | İngilizce |
| Basım Tarihi | 01-2024 |
| Cilt No | 42 |
| Sayı | 5 |
| Sayfalar | 18 / 1645 |
| DOI Numarası | 10.14744/sigma.2023.00106106 |
| Makale Linki | https://doi.org/10.14744/sigma.2023.00106 |
| Özet |
| In recent years, Internet of Things (IoT) applications have become across-the-board and are used by most smart device users. Wired Communication, Bluetooth, radio frequency (RF), RS485/Modbus, and zonal intercommunication global standard (ZigBee) can be used as IoT communication methods. The low delay times and ability to control homes from outside the building via the Internet are the main reasons wireless fidelity (Wi-Fi) communication is preferred. Commercially produced devices generally use their unique interfaces. The devices do not allow integration to form an intelligent home automation and demand-side energy management system. In addition, the high cost of most commercial products creates barriers for users. In this study, a local home automation server (LHAS) was created subject to low cost. Smart devices connected to the server through a Wi-Fi network were designed and implemented. The primary purpose of the design is to create an IoT network to form an LHAS. The IoT network will learn the energy consumption behavior of users for future Smart Grids. The designed intelligent devices can provide all the necessary measurements and control of houses. The open-source software Home Assistant (Hassio) was used to create the LHAS. Espressif systems (ESP) series microcontrollers (μCs) were chosen to design intelligent devices. ESP-01, NodeMCU, and ESP-32, the most widely used ESP models, were preferred. A convolutional neural network (CNN)/long short-term memory (LSTM) neural network was designed, and analysis was performed to learn the consumption behavior of residential users. |
| Anahtar Kelimeler |
| CNN-LSTM Neural Network | Database | Deep Learning | Demand-Side Energy Management | Esp-01, Esp8266, Esp32 | Future Smart Homes, And Smart Grids | Iot Network | Local Home Automation Server | Microcontroller | Monitor And Control | Smart Controller Board, Load Profiles | Wi-Fi Communication |
BM Sürdürülebilir Kalkınma Amaçları
| Atıf Sayıları | |
| WoS | 1 |
| SCOPUS | 1 |
| Google Scholar | 6 |