Comparison of KNN and LSTM on the Prediction of the Operational Conditions of Natural Gas Pipeline Transmission Networks

Afrizal Syahruluddin Yusuf
Hasmawati Hasmawati
Aditya Firman Ihsan


DOI: https://doi.org/10.29100/jipi.v9i2.4528

Abstract


During the gas distribution process, a sequence of compressors creates a pressure difference, causing gas to move from regions of high pressure to areas with comparatively lower pressure. The Natural Gas transmission process experiences variations in pressure and temperature, primarily caused by frictional losses, differences in altitude, gas velocity, and the Joule-Thompson effect. Additionally, effective heat transfer to or from the environment contributes to temperature changes throughout the pipeline. The presence of liquid and density changes (hydrate) within the channel also has an impact on the pressure, influencing both pressure and temperature conditions.. This study implements the KNN and LSTM models to predict pressure conditions in natural gas transmission pipelines to analyze the performance comparison of the best model performance using several appropriate parameters to support maximum method performance results. The results show that the LSTM model is better at predicting pressure conditions in natural gas pipeline transmission networks, with an R2 score of 99.45, compared to the KNN model, with an R2 score of 92.82. This study also obtained prediction results from the KNN and LSTM models; the KNN model tends to produce the same pressure value for eight months, while the LSTM model produces pressure values that tend to vary.

Keywords


forecasting; KNN; LSTM; pressure; pipeline transmission; natural gas

Full Text:

PDF

Article Metrics :

References


“Pipeline Basics & Specifics About Natural Gas Pipelines,” May 2015. Accessed: May 29, 2023. [Online]. Available: https://pstrust.org/wp-content/uploads/2015/09/2015-PST-Briefing-Paper-02-NatGasBasics.pdf

A. Mohd, S. Khan, S. Al, and I. Quraishy, “Pressure Drop Analysis of Natural Gas Transmission Line in Bangladesh.”

A. Nadwah and A. Faisol, “IMPLEMENTASI WEIGHTED K-NEAREST NEIGHBOR UNTUK PERAMALAN DATA DERET WAKTU,” J. Ris. & Ap. Mat, vol. 05, no. 02, pp. 111–117, 2021.

L. Wiranda and M. Sadikin, “PENERAPAN LONG SHORT TERM MEMORY PADA DATA TIME SERIES UNTUK MEMPREDIKSI PENJUALAN PRODUK PT. METISKA FARMA.”

C. C. Kurniawan, S. Rostianingsih, and L. W. Santoso, “Penerapan Metode KNN-Regresi dan Multiplicative Decomposition untuk Prediksi Data Penjualan pada Supermarket X.”

F. Martínez, M. P. Frías, F. Charte, and A. J. Rivera, “Time Series Forecasting with KNN in R: the tsfknn Package.”

I. Arimi, R. Purwaningsih, and Z. F. Rosyada, “METODE K-NEAREST NEIGHBOR UNTUK MEMPREDIKSI PENJUALAN PRODUK PADA UMKM PENGOLAHAN IKAN MAJU JAYA.”

Z. Wang, S. Ji, and B. Yu, “Short-Term Traffic Volume Forecasting with Asymmetric Loss Based on Enhanced KNN Method,” Math Probl Eng, vol. 2019, 2019, doi: 10.1155/2019/4589437.

A. F. Ihsam, Darmadi, S. Uttunggadewa, S. D. Rahmawati, I. Giovanni, and S. N. Himawan, “Multi-Layer LSTM Implementa-tion in Operational Condition Forecasting of a Natural Gas Transmission Pipeline Network,” in ICOIACT 2022 - 5th Interna-tional Conference on Information and Communications Technology: A New Way to Make AI Useful for Everyone in the New Normal Era, Proceeding, Institute of Electrical and Electronics Engineers Inc., 2022, pp. 244–249. doi: 10.1109/ICOIACT55506.2022.9971837.

S. R. Patra, H. J. Chu, and Tatas, “Regional groundwater sequential forecasting using global and local LSTM models,” J Hydrol Reg Stud, vol. 47, Jun. 2023, doi: 10.1016/j.ejrh.2023.101442.

F. Bayram, P. Aupke, B. S. Ahmed, A. Kassler, A. Theocharis, and J. Forsman, “DA-LSTM: A dynamic drift-adaptive learning framework for interval load forecasting with LSTM networks,” Eng Appl Artif Intell, vol. 123, Aug. 2023, doi: 10.1016/j.engappai.2023.106480.

A. F. Ihsan and W. Astuti, “Deep Learning Based Anomaly Detection on Natural Gas Pipeline Operational Data,” in 2022 2nd International Conference on Intelligent Cybernetics Technology and Applications, ICICyTA 2022, Institute of Electrical and Electronics Engineers Inc., 2022, pp. 228–233. doi: 10.1109/ICICyTA57421.2022.10037988.

A. F. Ihsan, Darmadi, and I. Fahmi, “Analysis of Deep Learning Performance in Hydrocarbon Dew Point Temperature Estima-tion in Gas Pipeline Network,” in 2022 10th International Conference on Information and Communication Technology, ICoICT 2022, Institute of Electrical and Electronics Engineers Inc., 2022, pp. 200–204. doi: 10.1109/ICoICT55009.2022.9914860.

N. R. Sari, W. F. Mahmudy, A. P. Wibawa, and E. Sonalitha, “Enabling external factors for inflation rate forecasting using fuzzy neural system,” International Journal of Electrical and Computer Engineering, vol. 7, no. 5, pp. 2746–2756, Oct. 2017, doi: 10.11591/ijece.v7i5.pp2746-2756.

M. N. Akhter et al., “An Hour-Ahead PV Power Forecasting Method Based on an RNN-LSTM Model for Three Different PV Plants,” Energies (Basel), vol. 15, no. 6, Mar. 2022, doi: 10.3390/en15062243.

M. Jamei et al., “Designing a decomposition-based multi-phase pre-processing strategy coupled with EDBi-LSTM deep learning approach for sediment load forecasting,” Ecol Indic, vol. 153, Sep. 2023, doi: 10.1016/j.ecolind.2023.110478.

C. Erden, “Genetic algorithm-based hyperparameter optimization of deep learning models for PM2.5 time-series prediction,” International Journal of Environmental Science and Technology, vol. 20, no. 3, pp. 2959–2982, Mar. 2023, doi: 10.1007/s13762-023-04763-6.

F. Li and G. Jin, “Research on power energy load forecasting method based on KNN,” International Journal of Ambient Ener-gy, vol. 43, no. 1, pp. 946–951, 2022, doi: 10.1080/01430750.2019.1682041.

M. Liu et al., “The applicability of lstm-knn model for real-time flood forecasting in different climate zones in China,” Water (Switzerland), vol. 12, no. 2, Feb. 2020, doi: 10.3390/w12020440.

H. Chen, M. Zhu, X. Hu, J. Wang, Y. Sun, and J. Yang, “Research on short-term load forecasting of new-type power system based on GCN-LSTM considering multiple influencing factors,” Energy Reports, vol. 9, pp. 1022–1031, Oct. 2023, doi: 10.1016/j.egyr.2023.05.048.

H. Kusdarwati and S. Handoyo, “System for prediction of non stationary time series based on the wavelet radial bases function neural network model,” International Journal of Electrical and Computer Engineering, vol. 8, no. 4, pp. 2327–2337, Aug. 2018, doi: 10.11591/ijece.v8i4.pp2327-2337.

Y. Abdillah and S. Suharjito, “Failure prediction of e-banking application system using adaptive neuro fuzzy inference system (ANFIS),” International Journal of Electrical and Computer Engineering (IJECE), vol. 9, no. 1, p. 667, Feb. 2019, doi: 10.11591/ijece.v9i1.pp667-675.