SMART CLASSIFICATION TECHNOLOGY MODELS (SCTM) PADA GEDUNG BERTINGKAT SEBAGAI PENGGERAK PLTB MENGGUNAKAN METODE RECURRENT NEURAL NETWORK
Total View This Week0
Total View This Week0
Institusion
Institut Teknologi Perusahaan Listrik Negara
Author
HAZIRAH, YASTAKUNA PUTRI
Indrianto, Indrianto
Haris, Abdul
Indrianto, Indrianto
Haris, Abdul
Subject
Teknik Informatika
Datestamp
2023-05-31 08:08:01
Abstract :
The need for renewable energy is increasing every year, it is predicted that the need for electrical energy will increase by up to 4.5% each year. Where this is caused by the growth of modern society. By looking for alternatives to meet the need for electrical energy by utilizing Indonesia's abundant wind potential. Where wind is flexible energy because it can be used anywhere. It is known that wind is energy that never runs out and can continue to be used as fuel or energy raw material. Utilizing the abundant potential of wind as a very promising renewable energy will fulfill electrical energy, renewable energy, namely Wind Power Generation (PLTB) is to process power from wind speed into electricity through wind turbines. One of the potential applications of wind energy is in multi-storey buildings that have a minimum building height of 23 to 30 meters in order to make a PLTB. Where the Jakarta PLN Institute of Technology is one of the universities in Jakarta which has a building height of 53.5 m making it very strategic. The purpose of this study is to classify wind data using the Recurrent Neural Network algorithm in order to find out whether the wind potential on the ITPLN campus has the potential for wind power generation. Recurrent Neural Network is a data mining method that groups data based on similarity. In this study, wind data was used in February with the time series data type. There are 3 classes of results, namely maximizing wind potential based on low, medium, and hight.
The need for renewable energy is increasing every year, it is predicted that the need for electrical energy will increase by up to 4.5% each year. Where this is caused by the growth of modern society. By looking for alternatives to meet the need for electrical energy by utilizing Indonesia's abundant wind potential. Where wind is flexible energy because it can be used anywhere. It is known that wind is energy that never runs out and can continue to be used as fuel or energy raw material. Utilizing the abundant potential of wind as a very promising renewable energy will fulfill electrical energy, renewable energy, namely Wind Power Generation (PLTB) is to process power from wind speed into electricity through wind turbines. One of the potential applications of wind energy is in multi-storey buildings that have a minimum building height of 23 to 30 meters in order to make a PLTB. Where the Jakarta PLN Institute of Technology is one of the universities in Jakarta which has a building height of 53.5 m making it very strategic. The purpose of this study is to classify wind data using the Recurrent Neural Network algorithm in order to find out whether the wind potential on the ITPLN campus has the potential for wind power generation. Recurrent Neural Network is a data mining method that groups data based on similarity. In this study, wind data was used in February with the time series data type. There are 3 classes of results, namely maximizing wind potential based on low, medium, and hight.
Download
book
BibTex
Latex, Jabref
cloud_download
Original Resource
url resource Institution
