Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 3

HYBRID SES-LSTM RECURRENT NEURAL NETWORK MODEL FOR TIME SERIES FORECASTING OF ELECTRICITY EXPENDITURE IN A UNIVERSITY

BAREKENG: Jurnal Ilmu Matematika dan Terapan · Vol. 20 No. 2 (2026) · hlm. 1757–1774

DOI
10.30598/barekengvol20iss2pp1757-1774
ISSN
2615-3017, 1978-7227
Terbit
2026-01-26
Penerbit
PATTIMURA UNIVERSITY
Bahasa
eng
Lisensi
creativecommons.org/licenses/by-sa/4.0

Abstrak

Efficient energy management has become a critical concern across all sectors due to rising costs and sustainability imperatives. In universities, electricity expenditure represents a substantial share of operational budgets, prompting the need for accurate forecasting models to support financial planning and sustainability initiatives. This study proposed a hybrid forecasting model integrating Simple Exponential Smoothing (SES) and Long Short-Term Memory (LSTM) networks to predict monthly electricity expenditure in a university setting. SES acts as a linear smoothing operator, emphasizing recent trends, while LSTM serves as a nonlinear sequence learner capable of modeling long-term dependencies. The hybrid formulation embeds SES forecasts as auxiliary input features to LSTM, thereby balancing interpretability with predictive power. A dataset of 60 monthly electricity expenditure observations (2019–2023) from Eastern Visayas State University–Tanauan Campus was analyzed. The proposed model was compared against classical (SES, ARIMA) and deep learning (LSTM, FB Prophet) approaches. Results show that the hybrid model achieved superior performance (RMSE = 33760.68, MAPE = 32.32%, MAE = 24580.12), with statistical validation through the Diebold-Mariano test, which confirmed significant improvements. Residual and uncertainty analyses demonstrated the model's robustness and practical applicability. The proposed model positioned it as a valuable decision-support tool for energy cost forecasting and risk-aware planning in universities.

Jaringan kolaborasi para penulis

2 penulis · 1 tautan kepenulisan bersama

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Eastern Visayas State University
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) https://ojs3.unpatti.ac.id/index.php/barekeng/oai, pertama di-harvest 5 Nov 2026, terakhir terlihat 15 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">HYBRID SES-LSTM RECURRENT NEURAL NETWORK MODEL FOR TIME SERIES FORECASTING OF ELECTRICITY EXPENDITURE IN A UNIVERSITY</dc:title>
	<dc:creator>Nadas Treceñe, Jasten Keneth De las</dc:creator>
	<dc:creator>Barbosa, Reynalyn O.</dc:creator>
	<dc:description xml:lang="en-US">Efficient energy management has become a critical concern across all sectors due to rising costs and sustainability imperatives. In universities, electricity expenditure represents a substantial share of operational budgets, prompting the need for accurate forecasting models to support financial planning and sustainability initiatives. This study proposed a hybrid forecasting model integrating Simple Exponential Smoothing (SES) and Long Short-Term Memory (LSTM) networks to predict monthly electricity expenditure in a university setting. SES acts as a linear smoothing operator, emphasizing recent trends, while LSTM serves as a nonlinear sequence learner capable of modeling long-term dependencies. The hybrid formulation embeds SES forecasts as auxiliary input features to LSTM, thereby balancing interpretability with predictive power. A dataset of 60 monthly electricity expenditure observations (2019–2023) from Eastern Visayas State University–Tanauan Campus was analyzed. The proposed model was compared against classical (SES, ARIMA) and deep learning (LSTM, FB Prophet) approaches. Results show that the hybrid model achieved superior performance (RMSE = 33760.68, MAPE = 32.32%, MAE = 24580.12), with statistical validation through the Diebold-Mariano test, which confirmed significant improvements. Residual and uncertainty analyses demonstrated the model's robustness and practical applicability. The proposed model positioned it as a valuable decision-support tool for energy cost forecasting and risk-aware planning in universities.</dc:description>
	<dc:publisher xml:lang="en-US">PATTIMURA UNIVERSITY</dc:publisher>
	<dc:date>2026-01-26</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://ojs3.unpatti.ac.id/index.php/barekeng/article/view/21561</dc:identifier>
	<dc:identifier>10.30598/barekengvol20iss2pp1757-1774</dc:identifier>
	<dc:source xml:lang="en-US">BAREKENG: Jurnal Ilmu Matematika dan Terapan; Vol 20 No 2 (2026): BAREKENG: Journal of Mathematics and Its Application; 1757-1774</dc:source>
	<dc:source>2615-3017</dc:source>
	<dc:source>1978-7227</dc:source>
	<dc:source>10.30598/barekengvol20iss2year2026</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://ojs3.unpatti.ac.id/index.php/barekeng/article/view/21561/12472</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2026 Jasten Keneth De las Nadas Treceñe, Reynalyn O. Barbosa</dc:rights>
	<dc:rights xml:lang="en-US">http://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>