Araştırma Makalesi

FORECASTING U.S. ENERGY CONSUMPTION BETWEEN 1973–2022, USING GRU, NARX AND 1D-CNN REGRESSION MODELS

Cilt: 14 Sayı: 3 25 Eylül 2026
PDF İndir
TR EN

FORECASTING U.S. ENERGY CONSUMPTION BETWEEN 1973–2022, USING GRU, NARX AND 1D-CNN REGRESSION MODELS

Öz

This paper analyzes 3 different deep learning models including Gated Recurrent Unit (GRU), Nonlinear Autoregressive model with Exogenous Inputs (NARX) and one-dimensional Convolutional Neural Network (1D-CNN), used to predict monthly energy consumption in the USA between 1973 and 2022 years, with realistic dataset containing 600 months of data. In this experiment the dataset is split into 70% training, 15% validation and 15% test sets. The time series were transformed into supervised learning sequences, each consisting of a 12-month lookback periods. In NARX model, a feature engineering process implemented using three exogenous inputs generated for each time step including a 3-month moving average, trend and volatility. The GRU and 1D-CNN models, in contrast, were trained directly on the raw time series sequences. The experimental results indicating recurrent architectures being exceptionally well-suited for this task, with GRU model achieving highest performance scores with R² of 0.85 with slight overfitting gap of 0.124 R² between training and test sets, and Mean Absolute Percentage Error of 3.16. The NARX model performed nearly as well as GRU model, achieving an R² of 0.846 and MAPE of 3.18, in contrast to 1D-CNN, resulting in a substantially lower R² of 0.648.

Anahtar Kelimeler

Kaynakça

  1. Aquila, G., et al., 2023. An Overview of Short-Term Load Forecasting for Electricity Systems Operational Planning: Machine Learning Methods and the Brazilian Experience. Energies, 16 (21).
  2. Arnob, S.S., Arefin, A.I.M.S., Saber, A.Y., Mamun, K.A., 2023. Energy Demand Forecasting and Optimizing Electric Systems for Developing Countries. IEEE Access, 11, 39751–39775.
  3. Bannor, E.B., Acheampong, A.O., 2019. Deploying Artificial Neural Networks for Modeling Energy Demand: International Evidence. International Journal of Energy Sector Management, 14 (2), 285–315.
  4. Box, G.E.P., Jenkins, G.M., 1970. Time Series Analysis: Forecasting and Control. Holden-Day, San Francisco.
  5. De Cian, E., Lanzi, E., Roson, R., 2007. The Impact of Climate Change on Energy Demand: A Dynamic Panel Analysis. Social Science Research Network, Rochester, NY, 1359045.
  6. Hasanat, S.M., et al., 2024. Enhancing Short-Term Load Forecasting With a CNN-GRU Hybrid Model: A Comparative Analysis. IEEE Access, 12, 184132–184141.
  7. Hernandez, L., et al., 2014. A Survey on Electric Power Demand Forecasting: Future Trends in Smart Grids, Microgrids and Smart Buildings. IEEE Communications Surveys & Tutorials, 16 (3), 1460–1495.
  8. Hossain, S., et al., 2025. Forecasting Energy Consumption Trends with Machine Learning Models for Improved Accuracy and Resource Management in the USA. Journal of Business and Management Studies, 7 (1), 200–217.

Ayrıntılar

Birincil Dil

İngilizce

Konular

Programlama Dilleri, Enerji

Bölüm

Araştırma Makalesi

Yayımlanma Tarihi

25 Eylül 2026

Gönderilme Tarihi

17 Şubat 2026

Kabul Tarihi

16 Haziran 2026

Yayımlandığı Sayı

Yıl 2026 Cilt: 14 Sayı: 3

Kaynak Göster

APA
Behzadisam, S., & Uğurenver, A. (2026). FORECASTING U.S. ENERGY CONSUMPTION BETWEEN 1973–2022, USING GRU, NARX AND 1D-CNN REGRESSION MODELS. Mühendislik Bilimleri ve Tasarım Dergisi, 14(3), 573-589. https://doi.org/10.21923/jesd.1891274
AMA
1.Behzadisam S, Uğurenver A. FORECASTING U.S. ENERGY CONSUMPTION BETWEEN 1973–2022, USING GRU, NARX AND 1D-CNN REGRESSION MODELS. MBTD. 2026;14(3):573-589. doi:10.21923/jesd.1891274
Chicago
Behzadisam, Shayan, ve Abbas Uğurenver. 2026. “FORECASTING U.S. ENERGY CONSUMPTION BETWEEN 1973–2022, USING GRU, NARX AND 1D-CNN REGRESSION MODELS”. Mühendislik Bilimleri ve Tasarım Dergisi 14 (3): 573-89. https://doi.org/10.21923/jesd.1891274.
EndNote
Behzadisam S, Uğurenver A (01 Eylül 2026) FORECASTING U.S. ENERGY CONSUMPTION BETWEEN 1973–2022, USING GRU, NARX AND 1D-CNN REGRESSION MODELS. Mühendislik Bilimleri ve Tasarım Dergisi 14 3 573–589.
IEEE
[1]S. Behzadisam ve A. Uğurenver, “FORECASTING U.S. ENERGY CONSUMPTION BETWEEN 1973–2022, USING GRU, NARX AND 1D-CNN REGRESSION MODELS”, MBTD, c. 14, sy 3, ss. 573–589, Eyl. 2026, doi: 10.21923/jesd.1891274.
ISNAD
Behzadisam, Shayan - Uğurenver, Abbas. “FORECASTING U.S. ENERGY CONSUMPTION BETWEEN 1973–2022, USING GRU, NARX AND 1D-CNN REGRESSION MODELS”. Mühendislik Bilimleri ve Tasarım Dergisi 14/3 (01 Eylül 2026): 573-589. https://doi.org/10.21923/jesd.1891274.
JAMA
1.Behzadisam S, Uğurenver A. FORECASTING U.S. ENERGY CONSUMPTION BETWEEN 1973–2022, USING GRU, NARX AND 1D-CNN REGRESSION MODELS. MBTD. 2026;14:573–589.
MLA
Behzadisam, Shayan, ve Abbas Uğurenver. “FORECASTING U.S. ENERGY CONSUMPTION BETWEEN 1973–2022, USING GRU, NARX AND 1D-CNN REGRESSION MODELS”. Mühendislik Bilimleri ve Tasarım Dergisi, c. 14, sy 3, Eylül 2026, ss. 573-89, doi:10.21923/jesd.1891274.
Vancouver
1.Shayan Behzadisam, Abbas Uğurenver. FORECASTING U.S. ENERGY CONSUMPTION BETWEEN 1973–2022, USING GRU, NARX AND 1D-CNN REGRESSION MODELS. MBTD. 01 Eylül 2026;14(3):573-89. doi:10.21923/jesd.1891274

Mühendislik Bilimleri ve Tasarım Dergisi (MBTD)

e-ISSN: 1308-6693 | Süleyman Demirel Üniversitesi Mühendislik ve Doğa Bilimleri Fakültesi

© 2026 Mühendislik Bilimleri ve Tasarım Dergisi (MBTD).

Bu dergide yayımlanan eserlerin telif ve kullanım koşulları, CC BY 4.0 lisansı kapsamında belirlenmiştir.