Scholarly record
THE IMPACT OF FORECASTING ON SUSTAINABLE HUMAN CAPITAL IN THE ENERGY SECTOR
Abstract
Sustainability in the energy sector depends not only on technological change and renewable energy development, but also on the capacity to ensure an adaptable and future-oriented workforce. Although forecasting methods are widely used in operational workforce planning, their role in supporting sustainable human capital development remains insufficiently explored. The aim of this study is to assess how forecasting-based approaches can support sustainable human capital development in the energy sector by identifying changes in labour demand, workforce capacity and capacity-related risks. The empirical analysis focuses on the Latvian energy sector, defined according to NACE 2 Section D. The study uses secondary statistical data from the Central Statistical Bureau of Latvia and the Ministry of Climate and Energy of the Republic of Latvia, including data on occupied jobs, vacancy rates and energy sector transformation indicators. A mixed analytical approach is applied, combining descriptive analysis, time series forecasting and indicator-based interpretation of human capital sustainability. ARIMA and seasonal SARIMA models are used to analyse time series patterns, while Gaussian Process Regression is applied as a comparative model for assessing forecast accuracy and uncertainty. Human capital sustainability is assessed through workforce capacity stability, vacancy pressure, skills alignment risks and the sector’s ability to adapt to projected demand changes. The results indicate a relatively stable but gradually increasing need for labour capacity in the Latvian energy sector during 2026-2028. The comparison of forecasting models shows that Gaussian Process Regression demonstrated the lowest forecast errors for the analysed workforce indicators. The findings show that forecasting can extend beyond operational planning by supporting early identification of capacity risks, more targeted skills development and evidence-based workforce planning.
Publication details
References14
Borba, B. S., Fortes, M. Z., Bitencourt, L. A., Ferreira, V. H., Maciel, R. S., Guimaraens, M. A., Moreira, B. S. (2019). A review on optimization methods for workforce planning in electrical distribution utilities. Computers & Industrial Engineering, 135, 286-298. Available: DOI: 10.1016/j.cie.2019.06.002
Cao, D., Zhao, J., Hu, W., Zhang, Y., Liao, Q., Chen, Z., Blaabjerg, F. (2021). Robust deep Gaussian process-based probabilistic electrical load forecasting against anomalous events. IEEE Transactions on Industrial Informatics, 18(2), 1142-1153. Available: DOI: 10.1109/TII.2021.3081531
Cedefop (2023). Skills in transition: the way to 2035. Luxembourg: Publications Office. Available: http://data.europa.eu/doi/DOI: 10.2801/438491
Energy Strategy Latvia 2050. (2026) Ministry of Climate and Energy of the Republic of Latvia. Available: https://www.kem.gov.lv
Gajewski, P., Cule, B., Rankovic, N. (2023). Unveiling the power of ARIMA, support vector and random forest regressors for the future of the Dutch employment market. Journal of Theoretical and Applied Electronic Commerce Research, 18(3), 1365-1403. Available: DOI: 10.3390/jtaer18030069
Huang, S. Z., Chien, F., Sadiq, M. (2022). A gateway towards a sustainable environment in emerging countries: the nexus between green energy and human Capital. Economic research, 35(1), Available: DOI: 10.1080/1331677X.2021.2012218
IEA (2023). World Energy Employment, 2023. Available: https://www.iea.org/reports/world-energy-employment-2023
IRENA & ILO. (2024). Renewable Energy and Jobs: Annual Review 2024. International Renewable Energy Agency and International Labour Organization. Available: https://www.ilo.org/publications/renewable-energy-and-jobs-annual-review
Klonowska-Matynia, M. (2025). Human Capital and the Sustainable Energy Transition: A Socio-Economic Perspective. Sustainability, 17(23), 10710. Available: DOI: 10.3390/su172310710
Marler, J. H., Boudreau, J. W. (2017). An evidence-based review of HR Analytics.The International Journal of Human Resource Management, 28(1), 3-26. Available: DOI: 10.1080/09585192.2016.1244699
Ng, K. Y., Zainal, Z., Samsudin, S. (2023). Comparative Performance of Arima, Sarima and Garch Models in Modelling and Forecasting Unemployment among Asean-5 Countries. Available: DOI: 10.33736/ijbs.6393.2023
Radulescu, M., Simionescu, M., Kartal, M. T., Mohammed, K. S., Balsalobre-Lorente, D. (2025). The Impact of Human Capital, Natural Resources, and Renewable Energy on Achieving Sustainable Cities and Communities in European Union Countries. Sustainability, 17(5), 2237. Available: DOI: 10.3390/su17052237
Safarishahrbijari, A. (2018). Workforce forecasting models: A systematic review. Journal of Forecasting, 37(7), 739-753. Available: DOI: 10.1002/for.2541
Yanamala, K. K. R. (2024). Strategic implications of AI integration in workforce planning and talent forecasting. Journal of Advanced Computing Systems, 4(1), 1-9. Available: DOI: 10.69987/JACS.2024.40101