https://doi.org/10.46793/TIL2025.054M

ANFIS-Based Prediction of Energy Generation Influence on Electrical Demand and Price in Smart Energy Logistics

Authors:

Abstract: The growing complexity of modern energy systems requires intelligent methods for managing the balance between generation, demand, and market dynamics. This paper presents an Adaptive Neuro-Fuzzy Inference System (ANFIS) model developed to predict the influence of different energy generation types on actual electrical demand and energy prices within smart energy logistics. The proposed approach integrates neuro-fuzzy reasoning to handle nonlinear relationships and uncertainty inherent in hybrid renewable systems. A comprehensive dataset covering four years of hourly electricity generation, consumption, and market prices in Spain was analyzed. Fourteen types of generation sources were considered, including fossil, hydro, nuclear, wind, and solar. The ANFIS-based model was implemented in MATLAB, using exhaustive search procedures to identify the most influential attributes for accurate forecasting. Results indicate that hydro pumped storage consumption (GHPSC) and wind onshore generation have the strongest joint impact on actual load demand, while the combination of GHPSC and fossil gas generation most significantly affects energy price variability. The findings confirm that ANFIS provides robust prediction capabilities with strong generalization and noise resistance, making it suitable for sustainable and data-driven energy management systems. The research contributes to the advancement of smart energy logistics by offering a flexible predictive framework that supports decision-making in hybrid power systems and energy market operations.

Keywords: energy generation, energy logistics, electrical price, forecasting, ANFIS

Pages: 54-62

The paper is available at the following link:

REFERENCES:

[1] Kahwash, F., Maheri, A., & Mahkamov, K. (2021). Integration and optimisation of high-penetration Hybrid Renewable Energy Systems for fulfilling electrical and thermal demand for off-grid communities. Energy Conversion and Management, 236, 114035.
[2] Wang, C., Zhang, Z., Abedinia, O., & Farkoush, S. G. (2021). Modeling and analysis of a microgrid considering the uncertainty in renewable energy resources, energy storage systems and demand management in electrical retail market. Journal of Energy Storage, 33, 102111.
[3] Bidgoli, M. M., Karimi, H., Jadid, S., & Anvari-Moghaddam, A. (2021). Stochastic electrical and thermal energy management of energy hubs integrated with demand response programs and renewable energy: A prioritized multi-objective framework. Electric Power Systems Research, 196, 107183.
[4] Jebaseelan, S. S., Selvan, N. M., Kumar, C., Kalaimurugan, A., Srujana, A., & Ravi, C. N. (2021). Solving constrained economic electrical energy generation and CO2 emission dispatch using hybrid algorithm. Environmental Technology & Innovation, 101999.
[5] Kotowicz, J., & Uchman, W. (2021). Analysis of the integrated energy system in residential scale: Photovoltaics, micro-cogeneration and electrical energy storage. Energy, 227, 120469.
[6] Yuan, G., Gao, Y., & Ye, B. (2021). Optimal dispatching strategy and real-time pricing for multi-regional integrated energy systems based on demand response. Renewable Energy, 179, 1424-1446.
[7] Gómez-Omella, M., Esnaola-Gonzalez, I., Ferreiro, S., & Sierra, B. (2021). k-Nearest patterns for electrical demand forecasting in residential and small commercial buildings. Energy and Buildings, 253, 111396.
[8] Taghizadeh, M., Bahramara, S., Adabi, F., & Nojavan, S. (2020). Optimal thermal and electrical operation of the hybrid energy system using interval optimization approach. Applied Thermal Engineering, 169, 114993.
[9] Zhang, L., Gao, Y., Zhu, H., & Tao, L. (2022). Bi-level stochastic real-time pricing model in multi-energy generation system: A reinforcement learning approach. Energy, 239, 121926.
[10] Jang, J.-S.R, ANFIS: Adaptive-Network-based Fuzzy Inference Systems, IEEE Trans. On Systems, Man, and Cybernetics (1993), Vol.23, 665-685.
[11] I. Mladenović, D. Marković, M. Milovančević, and M. Nikolić, “Extreme learning approach with wavelet transform function for forecasting wind turbine wake effect to improve wind farm efficiency,” Advances in Engineering Software, vol. 96, pp. 91–95, 2016, doi: 10.1016/ j.advengsoft.2016.02.011.
[12] V. Nikolić, J. Kaljević, S. Jović, D. Petković, M. Milovančević, L. Dimitrov, and P. Dachkinov, “Survey of quality models of e-learning systems,” Physica A: Statistical Mechanics and its Applications, vol. 511, pp. 324–330, 2018, doi: 10.1016/j.physa.2018.07.058.
[13] B. Novković-Cvetković, M. Gligorijević, D. Petković, S. Jović, M. Milovančević, and V. Nikolić, “Evaluation of information and communication technology sector in the teaching process and strategic collaboration between universities and industry,” Computer Applications in Engineering Education, vol. 27, no. 3, pp. 653–662, 2019, doi: 10.1002/cae.22105.
[14] H. Deneva, E. Teirumenieka, L. Lazov, V. Nikolić, and M. Milovančević, “Analysis of the influence of auxiliary gas pressure on cut characteristics of laser cut steel,” Lasers in Engineering, vol. 40, no. 4–6, pp. 253–263, 2017, doi: 10.1016/j.infrared.2018.04.007.
[15] B. Jokanović, B. Lalić, M. Milovančević, N. Simeunović, and D. Marković, “Economic development evaluation based on science and patents,” Physica A: Statistical Mechanics and its Applications, vol. 481, pp. 141–145, 2017, doi: 10.1016/j.physa.2017.04.015.
[16] V. Nikolić, M. Milovančević, D. Petković, D. Jocić, and M. Savić, “Parameters forecasting of laser welding by the artificial intelligence techniques,” Facta Universitatis, Series: Mecha–nical Engineering, vol. 16, no. 2, pp. 193–201, 2018, doi: 10.22190/FUME180526025N.