Performance of PSO and GWO Optimized Triple Exponential Smoothing for Rice Forecasting

Abd. Hadi; Lilis Widayanti; Budi  Santoso

doi:10.22146/jnteti.v15i2.24219

Abd. Hadi Informatics Study Program, Faculty of Technology and Design, Institut Teknologi dan Bisnis Asia, Malang, Jawa Timur 65113, Indonesia
Lilis Widayanti Computer System Study Program, Faculty of Technology and Design, Institut Teknologi dan Bisnis Asia, Malang, Jawa Timur 65113, Indonesia
Budi Santoso Computer System Study Program, Faculty of Technology and Design, Institut Teknologi dan Bisnis Asia, Malang, Jawa Timur 65113, Indonesia

DOI: https://doi.org/10.22146/jnteti.v15i2.24219

Keywords: Rice Production, Triple Exponential Smoothing, Particle Swarm Optimization, Grey Wolf Optimization, Tuning Parameter, Forecasting

Abstract

Rice production forecasting is crucial for supporting food security policies, where Indonesia’s food security remains a key goal of the current government, particularly in a developing city like Malang. Triple exponential smoothing (TES) is a suitable and reliable forecasting method for limited, univariate, and seasonal data. TES is a statistical method whose accuracy depends on parameter selection, which is typically determined through trial and error. This study aimed to evaluate the results of TES forecasting optimized using well-known metaheuristic algorithms, particle swarm optimization (PSO) and grey wolf optimization (GWO). The novelty of this study lies in comparing the performance of PSO and GWO for TES optimization on limited rice production data in Malang City. The training data was rice production data for 2022–2024, and the testing data is rice production data for 2025. The study found that the accuracy of rice production forecasting using the pure TES method varied, with mean absolute percentage error (MAPE) ranging from 31.11% to 89.69%. Meanwhile, optimization significantly reduced the MAPE to 19.96% for PSO and 20.90% for GWO. The results showed that PSO produced a smaller standard deviation than GWO, indicating that PSO produces more stable forecasting results. However, at 100 iterations, GWO had a computation time of 0.078 s, shorter than PSO’s 0.136 s. The research findings recommend the use of metaheuristic algorithms to optimize rice production forecasting with limited and univariate data. Combining forecasting methods such as TES with metaheuristic algorithms has been shown to reduce MAPE, thereby improving forecasting accuracy.

References

Sutardi et al., “The transformation of rice crop technology in Indonesia: Innovation and sustainable food security,” Agronomy, vol. 13, no. 1, pp. 1–14, Jan. 2023, doi: 10.3390/agronomy13010001.

A. Ansari et al., “Evaluating the effect of climate change on rice production in Indonesia using multimodelling approach,” Heliyon, vol. 9, no. 9, pp. 1–15, Sep. 2023, doi: 10.1016/j.heliyon.2023.e19639.

R. Ismail et al., “Climate change adaptation knowledge among rice farmers in Lake Toba Highland, Indonesia,” Sustainability, vol. 17, no. 13, pp. 1–16, Jul. 2025, doi: 10.3390/su17135715.

R. Arifin et al., “Indonesian sustainable development policy: How the government ensures the environment for future generations,” in IOP Conf. Ser., Earth Environ. Sci., 2024, pp. 1–6, doi: 10.1088/1755-1315/1355/1/012005.

L. Gandharum et al., “Advancing land use modeling with rice cropping intensity: A geospatial study on the shrinking paddy fields in Indonesia,” Geographies, vol. 5, no. 3, pp. 1–27, Sep. 2025, doi: 10.3390/geographies5030031.

I.N.H. Maulana et al., “Understanding urban farming as food security for community resilience: A study in Malang City,” Ecoplan, vol. 6, no. 2, pp. 130–144, Oct. 2023, doi: 10.20527/ecoplan.v6i2.671.

J. Zhang, C. Shen, Y. Qin, and J. Chen, “Forecasting of natural gas based on a novel discrete grey seasonal prediction model with a time power term,” Energy Strategy Rev., vol. 58, pp. 1–15, Mar. 2025, doi: 10.1016/j.esr.2025.101677.

R. Gong and X. Li, “A short-term load forecasting model based on crisscross grey wolf optimizer and dual-stage attention mechanism,” Energies, vol. 16, no. 6, pp. 1–24, Mar. 2023, doi: 10.3390/en16062878.

P. Sharma, P. Dadheech, N. Aneja, and S. Aneja, “Predicting agriculture yields based on machine learning using regression and deep learning,” IEEE Access, vol. 11, pp. 111255–111264, Oct. 2023, doi: 10.1109/ACCESS.2023.3321861.

A.A. Pertiwi and N.H. Harani, “Model terpopuler untuk prediksi harga bahan pokok: Sebuah tinjauan literatur,” JATI, J. Mhs. Tek. Inform., vol. 9, no. 5, pp. 7865–7873, Oct. 2025, doi: 10.36040/jati.v9i5.14927.

N. Annamalai and A. Johnson, “Analysis and forecasting of area under cultivation of rice in India: Univariate time series approach,” SN Comput. Sci., vol. 4, no. 2, pp. 1–8, Feb. 2023, doi: 10.1007/s42979-022-01604-0.

L. Widayanti, A.N. Afandi, H.W. Herwanto, and V.A. Fitria, “Metaheuristic optimization in dynamic unit commitment of power systems: Current trends and future prospects,” JOIV Int. J. Informatics Vis., vol. 8, no. 4, pp. 2261–2272, Dec. 2024, doi: 10.62527/joiv.8.4.2423.

H.L. Aisya, B.N. Apriliana, and H. Andriani, “Meramal produksi padi nasional: Pendekatan moving average dan triple exponential smoothing,” Indones. J. Appl. Stat. Data Sci., vol. 2, no. 2, pp. 92–103, Nov. 2025, doi: 10.29303/ijasds.v2i2.8494.

N.A. Lathifah, D. Nurdiansyah, and A.Y. Kartini, “Comparison of decomposition and triple exponential smoothing methods to improve rice production forecasting in East Java Province,” Vygotsky, J. Pendidik. Mat. Mat., vol. 7, no. 1, pp. 15–26, Feb. 2025, doi: 10.30736/voj.v7i1.1119.

S.J.E. Parreño, “Forecasting quarterly rice and corn production in the Philippines: A comparative study of seasonal ARIMA And Holt-Winters models,” ICTACT J. Soft Comput., vol. 14, no. 2, pp. 3224–3231, Oct. 2023, doi: 10.21917/ijsc.2023.0452.

A. Mumuni and F. Mumuni, “Automated data processing and feature engineering for deep learning and big data applications: A survey,” J. Inf. Intell., vol. 3, no. 2, pp. 113–153, Mar. 2025, doi: 10.1016/j.jiixd.2024.01.002.

M. Lallawmzuali and S. Muniyan, “Rainfall prediction in Mizoram using the modified Holt Winters method,” Theor. Appl. Climatol., vol. 156, pp. 1–12, Jan. 2025, doi: 10.1007/s00704-025-05354-w.

S.B. Atoyebi, M.F. Olayiwola, J.O. Oladapo, and D.I. Oladapo, “Forecasting currency in circulation in Nigeria using Holt-Winters exponential smoothing method,” South Asian J. Soc. Stud. Econ., vol. 20, no. 1, pp. 25–41, Jul. 2023, doi: 10.9734/sajsse/2023/v20i1689.

C. Deng, X. Zhang, Y. Huang, and Y. Bao, “Equipping seasonal exponential smoothing models with particle swarm optimization algorithm for electricity consumption forecasting,” Energies, vol. 14, no. 13, pp. 1–14, Jul. 2021, doi: 10.3390/en14134036.

L. Widayanti, A.N. Afandi, and H.W. Herwanto, “Modified orca algorithm based on the navigation behavior for optimal unit commitment in power systems,” Bul. Ilm. Sarj. Tek. Elekt., vol. 7, no. 3, pp. 450–467, Sep. 2025, doi: 10.12928/biste.v7i3.13645.

M. Varan, A. Erduman, and F. Menevşeoğlu, “A grey wolf optimization algorithm-based optimal reactive power dispatch with wind-integrated power systems,” Energies, vol. 16, no. 13, pp. 1–28, Jul. 2023, doi: 10.3390/en16135021.

E.-S.M. El-kenawy et al., “Feature selection in wind speed forecasting systems based on meta-heuristic optimization,” PLoS ONE, vol. 18, no. 2, pp. 1–28, Feb. 2023, doi: 10.1371/journal.pone.0278491.

B. Gao, H. Guan, W. Shen, and Y. Ye, “Application of the gray wolf optimization algorithm in active disturbance rejection control parameter tuning of an electro-hydraulic servo unit,” Machines, vol. 10, no. 8, pp. 1–20, Aug. 2022, doi: 10.3390/machines10080599.

“Luas Panen dan Produksi Padi di Kota Malang Tahun 2022,” BPS-Statistics Malang Municipality, 2023.

“Luas Panen dan Produksi Padi di Kota Malang 2025,” BPS-Statistics Malang Municipality, 2025.

T.M. Baykal, H.E. Colak, and C. Kılınc, “Forecasting future climate boundary maps (2021–2060) using exponential smoothing method and GIS,” Sci. Total Environ., vol. 848, pp. 1–12, Nov. 2022, doi: 10.1016/j.scitotenv.2022.157633.

D.K. Hakim, R. Gernowo, and A.W. Nirwansyah, “Rainfall, wind speed, and temperature forecast using triple exponential smoothing and gradient descent,” in 6th Int. Conf. Educ. Soc. Sci. Res. (6th ICESRE), 2024, pp. 578–590, doi: 10.18502/kss.v9i6.15311.

D.A. Rahim, I. Citarayani, and M.C. Marbun, “Linking financial performance to profit growth: Empirical insights from pharmaceutical firms in Indonesia,” E-J. Akunt., vol. 35, no. 6, pp. 1772–1787, Jun. 2025, doi: 10.24843/EJA.2025.v35.i06.p18.

A.D. Az-Zahra, L.A. Fajriati, and S.D. Sari, “Forecasting the number of dropout student in Indonesia using ARIMA model,” JTAM (J. Teori Apl. Mat.), vol. 9, no. 3, pp. 839–853, Jul. 2025, doi: 10.31764/jtam.v9i3.31625.

D.-D. Ramírez-Ochoa, L.A. Pérez-Domínguez, E.-A. Martínez-Gómez, and D. Luviano-Cruz, “PSO, a swarm intelligence-based evolutionary algorithm as a decision-making strategy: A review,” Symmetry, vol. 14, no. 3, pp. 1–23, Mar. 2022, doi: 10.3390/sym14030455.

A. Robson, K. Mistry, and W.-L. Woo, “A novel group-based framework for nature-inspired optimization algorithms with adaptive movement behavior,” Complex Intell. Syst., vol. 11, pp. 1–21, Jan. 2025, doi: 10.1007/s40747-024-01763-y.

A.D. Boursianis et al., “Emerging swarm intelligence algorithms and their applications in antenna design: The GWO, WOA, and SSA optimizers,” Appl. Sci., vol. 11, no. 18, pp. 1–27, Sep. 2021, doi: 10.3390/app11188330.

I. Sharma, V. Kumar, and S. Sharma, “A comprehensive survey on grey wolf optimization,” Recent Adv. Comput. Sci. Commun., vol. 15, no. 3, pp. 323–333, Oct. 2022, doi: 10.2174/2666255813999201007165454.

E. Dada et al., “Application of grey wolf optimization algorithm: Recent trends, issues, and possible horizons,” Gazi Univ. J. Sci., vol. 35, no. 2, pp. 485–504, Jun. 2022, doi: 10.35378/gujs.820885.

X. Sun et al., “A new algorithm for predicting dam deformation using grey wolf-optimized variational mode long short-term neural network,” Remote Sens., vol. 16, no. 21, pp. 1–19, Nov. 2024, doi: 10.3390/rs16213978.

M. Jain, V. Saihjpal, N. Singh, and S.B. Singh, “An overview of variants and advancements of PSO algorithm,” Appl. Sci., vol. 12, no. 17, pp. 1–21, Sep. 2022, doi: 10.3390/app12178392.

J. Wang, X. Wang, X. Li, and J. Yi, “A hybrid particle swarm optimization algorithm with dynamic adjustment of inertia weight based on a new feature selection method to optimize SVM parameters,” Entropy, vol. 25, no. 3, pp. 1–23, Mar. 2023, doi: 10.3390/e25030531.

A. Ashraf, A.A. Almazroi, W.H. Bangyal, and M.A. Alqarni, “Particle swarm optimization with new initializing technique to solve global optimization problems,” Intell. Autom. Soft Comput., vol. 31, no. 1, pp. 191–206, Sep. 2021, doi: 10.32604/iasc.2022.015810.

Ö.T. Ebesek and Ş. Ebesek, “Optimizing Holt-Winters exponential smoothing parameters for construction cost index forecasting with PSO and walk-forward cross-validation,” Kent Akad., vol. 16, no. 4, pp. 2422–2439, Dec. 2023, doi: 10.35674/kent.1343590.

V.A. Fitria and L. Widayanti, “Enhancing accuracy in stock price prediction: The power of optimization algorithms,” MATRIK, vol. 23, no. 2, pp. 405–418, Mar. 2024, doi: 10.30812/matrik.v23i2.3785.

G.H.H. Nayak et al., “Meta-transformer: leveraging metaheuristic algorithms for agricultural commodity price forecasting,” J. Big Data, vol. 12, pp. 1–29, May 2025, doi: 10.1186/s40537-025-01196-5.