PREDIKSI KEBUTUHAN AIR PDAM DENGAN ALGORITMA ELMAN RECURRENT NEURAL NETWORK

dc.contributor.authorManaf, Akhyarni
dc.contributor.supervisorFitriansyah, Aidil
dc.date.accessioned2022-06-20T04:44:40Z
dc.date.available2022-06-20T04:44:40Z
dc.date.issued2021-12
dc.description.abstractThe government established PDAM to provide clean water services for the community in a fair and equitable manner. An increase in the number of customers can become a serious problem when it is not balanced with the capacity provided. By knowing the water demand in the future period, the water deficit can be prevented. The purpose of this study was to predict the volume of water demand for non-commercial user groups or households at BPAB Tandun, Rokan Hulu Regency using the Elman Recurrent Neural Network (ERNN) algorithm. The data used is the total monthly water volume for 5 years from January 2015 to December 2019 which is compiled in time series. In this study, it was found that the demand for water increases every year with a seasonal pattern and the highest volume is in December. From the evaluation results it was found that the best model could predict PDAM water demand for the next 12 months with an MSE value of 0.0403 or 4% (<10%). The model succeeded in recognizing the pattern of water demand with the best prediction results in the 4th month (April) and the 7th month (July). So it can be concluded that the Elman Recurrent Neural Network (ERNN) algorithm is suitable for making predictions.en_US
dc.description.sponsorshipJurusan Ilmu Komputer Fakultas Matematika dan Ilmu Pengetahuan Alamen_US
dc.identifier.citationPerpustakaanen_US
dc.identifier.issnElfitra
dc.identifier.urihttps://repository.unri.ac.id/handle/123456789/10552
dc.language.isoenen_US
dc.publisherElfitraen_US
dc.subjectPredictionen_US
dc.subjectWater Demanden_US
dc.subjectPDAMen_US
dc.subjectElman Recurrent Neural Networken_US
dc.titlePREDIKSI KEBUTUHAN AIR PDAM DENGAN ALGORITMA ELMAN RECURRENT NEURAL NETWORKen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
AKHYARNI MANAF.pdf
Size:
857.56 KB
Format:
Unknown data format
Description:
artikel
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections