Urban Electricity Consumption Forecasting Based on SARIMA and Random Forest Modeling
DOI: 10.23977/jeeem.2024.070115 | Downloads: 5 | Views: 136
Author(s)
Sijian Zhao 1
Affiliation(s)
1 School of Statistics and Mathematics, Yunnan University of Finance and Economics, Wuhua District, Kunming City, Yunnan Province, 650221, China
Corresponding Author
Sijian ZhaoABSTRACT
This project proposes to use a combination of machine learning and time series analysis to provide in-depth analysis and forecasting of electricity consumption in a city in North Africa. The dataset used in this study contains a range of information including date, temperature, humidity, wind speed, total flow, and electricity consumption. The project proposes to reveal patterns and patterns of electricity consumption behavior through data preprocessing, normalization, and seasonal decomposition. The project proposes to use two models: Seasonal Autoregressive Integrated Sliding Average (SARIMA) and Random Forest based on feature engineering. The SARIMA method is used to analyze the seasonality and trend of the time series data, and the Random Forest method is used to study the nonlinear relationship between electricity consumption and environmental factors. On this basis, we add more information such as rolling rolling standard deviation, minimum large value, and time-delayed features to the random forest. This method greatly improves the prediction accuracy of power consumption. The experimental results show that compared with the single SARIMA model, the random forest model using j combined with the feature engineering method can better predict the load changes of the power system. The results show that the Random Forest model can capture the complexity of power consumption more effectively, especially after adding detailed feature items. At the same time, the good interpretability and flexibility of Random Forest makes the model able to better understand and predict the urban power demand, which can effectively help the power grid enterprises to realize the optimal allocation of resources and reduce energy consumption.
KEYWORDS
Power Consumption Forecasting, SARIMA, Random Forest, Time Series Analysis, Machine LearningCITE THIS PAPER
Sijian Zhao, Urban Electricity Consumption Forecasting Based on SARIMA and Random Forest Modeling. Journal of Electrotechnology, Electrical Engineering and Management (2024) Vol. 7: 113-118. DOI: http://dx.doi.org/10.23977/jeeem.2024.070115.
REFERENCES
[1] Jiang, P., Li, R., Lu, H. et al. Modeling of electricity demand forecast for power system. Neural Comput & Applic 32, 6857–6875 (2020).
[2] Liu, Y. Q., & Chen, X. F. (2023). Research on Power Consumption Forecasting Based on CNN+LSTM Hybrid Model. Computer and Telecommunications, (07), 0065-0070.
[3] Daneshi, Hossein, and Ali Daneshi. "Real time load forecast in power system." 2008 Third International Conference on Electric Utility Deregulation and Restructuring and Power Technologies. IEEE, 2008.
[4] Niyozov N N, Rikhsitillaev B K, Jalilova D A, et al. Forecasting of electricity consumption by industrial enterprises with a continuous nature of production based on the principal component method (PCA)[C]//E3S Web of Conferences. EDP Sciences, 2023, 384: 01031.
[5] Bilgili M, Pinar E. Gross electricity consumption forecasting using LSTM and SARIMA approaches: A case study of Türkiye [J]. Energy, 2023, 284: 128575.
[6] Zhang, Jingxin. Mathematical Modeling: Algorithms and Programming Implementations. Beijing: China Machine Press, 2022.
[7] Géron, Aurélien. Hands-On Machine Learning with Scikit-Learn and TensorFlow. Beijing: Mechanical Industry Press, 2018.
[8] https://archive.ics.uci.edu/dataset/849/power+consumption+of+tetouan+city
Downloads: | 2443 |
---|---|
Visits: | 105616 |
Sponsors, Associates, and Links
-
Power Systems Computation
-
Internet of Things (IoT) and Engineering Applications
-
Computing, Performance and Communication Systems
-
Journal of Artificial Intelligence Practice
-
Advances in Computer, Signals and Systems
-
Journal of Network Computing and Applications
-
Journal of Web Systems and Applications
-
Journal of Wireless Sensors and Sensor Networks
-
Journal of Image Processing Theory and Applications
-
Mobile Computing and Networking
-
Vehicle Power and Propulsion
-
Frontiers in Computer Vision and Pattern Recognition
-
Knowledge Discovery and Data Mining Letters
-
Big Data Analysis and Cloud Computing
-
Electrical Insulation and Dielectrics
-
Crypto and Information Security
-
Journal of Neural Information Processing
-
Collaborative and Social Computing
-
International Journal of Network and Communication Technology
-
File and Storage Technologies
-
Frontiers in Genetic and Evolutionary Computation
-
Optical Network Design and Modeling
-
Journal of Virtual Reality and Artificial Intelligence
-
Natural Language Processing and Speech Recognition
-
Journal of High-Voltage
-
Programming Languages and Operating Systems
-
Visual Communications and Image Processing
-
Journal of Systems Analysis and Integration
-
Knowledge Representation and Automated Reasoning
-
Review of Information Display Techniques
-
Data and Knowledge Engineering
-
Journal of Database Systems
-
Journal of Cluster and Grid Computing
-
Cloud and Service-Oriented Computing
-
Journal of Networking, Architecture and Storage
-
Journal of Software Engineering and Metrics
-
Visualization Techniques
-
Journal of Parallel and Distributed Processing
-
Journal of Modeling, Analysis and Simulation
-
Journal of Privacy, Trust and Security
-
Journal of Cognitive Informatics and Cognitive Computing
-
Lecture Notes on Wireless Networks and Communications
-
International Journal of Computer and Communications Security
-
Journal of Multimedia Techniques
-
Automation and Machine Learning
-
Computational Linguistics Letters
-
Journal of Computer Architecture and Design
-
Journal of Ubiquitous and Future Networks