Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jul 1;15(1):20909.
doi: 10.1038/s41598-025-05083-0.

Novel machine learning approach for enhanced smart grid power use and price prediction using advanced shark Smell-Tuned flexible support vector machine

Yuwei Duan  1 , Zihan Xu  2 , Huiyi Chen  2 , Yue Wang  2
Affiliations

Novel machine learning approach for enhanced smart grid power use and price prediction using advanced shark Smell-Tuned flexible support vector machine

Yuwei Duan et al. Sci Rep. .

Abstract

Energy management has enhanced sustainability, dependability, and efficiency in smart grids. Urbanisation, technology, and consumer behaviour have boosted need for innovative power use and price control systems. The paper intends to construct ML for smart grid power use and price prediction. This work used an advanced shark smell-tuned flexible support vector machine (ASS-FSVM) to forecast smart grid price and power use. Weather stations, smart meters, and market price databases document power use and pricing. The quality and consistency of data are enhanced via the processes of cleaning and normalizing inputs. PCA reduces dimensionality by extracting pre-processed data characteristics. Optimized and tested FSVM models can anticipate smart grid power use and pricing. ASS may identify the most important dataset properties. The research evaluates electricity consumption forecasting using accuracy (98.05%), recall (98.93%), precision (97.10%), and F1-score (98.04%), and electricity price predicting using MAPE (4.32%), RMSE (5.80%), MSE (8.50%), and MAE (2.95%). The recommended strategy greatly increases forecast accuracy, helping utilities improve grid stability, demand responsiveness, and customer pricing.

Keywords: Advanced shark smell tuned flexible support vector machines (ASS-FSVM); Electricity consumption; Pricing; Principal component analysis (PCA); Smart grids.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Prediction process of the electricity consumption.
Fig. 2
Fig. 2
Methodological Flow.
None
Algorithm 1: Advanced Shark Smell-Tuned Flexible Support Vector Machine (ASS-FSVM)
Fig. 3
Fig. 3
Comparative Analysis of Different Models.
Fig. 4
Fig. 4
Comparative errors analysis of different models based on 3-D column diagram.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Avancini, D. B. et al. A new IoT-based smart energy meter for smart grids. Int. J. Energy Res.45 (1), 189–202 (2021).
    1. Kim, M. K., Kim, Y. S. & Srebric, J. Predictions of electricity consumption in a campus building using occupant rates and weather elements with sensitivity analysis: Artificial neural network vs. linear regression. Sustainable Cities and Society, 62, p.102385. (2020).
    1. Mbey, C. F., FobaKakeu, V. J., Boum, A. T. & YemSouhe, F. G. Solar photovoltaic generation and electrical demand forecasting using multi-objective deep learning model for smart grid systems. Cogent Engineering, 11(1), p.2340302. (2024).
    1. Souhe, F. G. Y., Mbey, C. F., Boum, A. T. & Ele, P. Forecasting of electrical energy consumption of households in a smart grid. Int. J. Energy Econ. Policy. 11 (6), 221–233 (2021).
    1. Aguiar-Pérez, J. M. & Pérez-Juárez, M. Á. An insight into deep learning-based demand forecasting in smart grids. Sensors, 23(3), p.1467. (2023). - PMC - PubMed

LinkOut - more resources