Claim Missing Document
Check
Articles

Found 1 Documents
Search

Implementasi Algoritme Extreme Learning Machine (ELM) untuk Prediksi Beban Pemanasan dan Pendinginan Bangunan Alif Fachrony; Imam Cholissodin; Edy Santoso
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 9 (2018): September 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (667.445 KB)

Abstract

Energy conservation is a very important thing as the growth of the times and technology. Making energy-efficient buildings needs to be done by optimizing the use of tools for cooling and heating the building without affecting the health and comfort of the user of the building. Energy-efficient buildings can be achieved by calculate heating (HL) and cooling (CL) loads. HL and CL are the heat flow rates to be taken or added from the building to maintain relative air temperature and humidity of the building under desired conditions. The prediction of HL and CL will be used in calculating the power loads of heater or air conditioner. Currently HL and CL calculations still have constraints such as very complex calculations, time consuming because many disciplines are involved and it use very varied parameters. It needs learning machine to predict HL and CL easily, and quickly. The author uses the algorithm Extreme Machine Learning (ELM) to predict HL and CL. In the test analysis using ELM algorithm performed using binary sigmoid activation function, 3 input, 1 hidden neurons, 2 output targets and 130 dataset, the best Mean Absolute Error Percentage (MAPE) is 24.73% and it takes 0.0176 seconds to complete the process.