Short-term Load Forecasting Considering EV Charging Loads with Prediction Interval Evaluation

Journal Article · Sun Oct 13 00:00:00 EDT 2024 · North American Power Symposium

DOI:https://doi.org/10.1109/naps61145.2024.10741734· OSTI ID:2539844

Shi, Naihao ^[1]; Zhang, Feixiang ^[1]; Wang, Zhaoyu ^[1]; MacDonald, Jason S. ^[2]; Baudette, Maxime ^[2]; Lin, Yashen ^[3]; Motakatla, Venkateswara ^[3]

---

1. Iowa State University, Ames, IA (United States)
2. Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
3. National Renewable Energy Laboratory (NREL), Golden, CO (United States)

Short-term load forecasting plays a critical role in power system planning and operation. Along with the electrification of various loads, electricity demands are becoming increasingly hard to predict. Notably, the recent rise in electric vehicles (EVs) has further contributed to this unpredictability. To address this issue, this paper proposes a probabilistic load forecasting strategy utilizing Gaussian process regression, structured in a day-ahead manner. While many works focus on deterministic prediction, probabilistic forecasting offers additional insights into variability and uncertainty, enabling more flexible and reliable operation for power systems. To enhance the accuracy of the load forecasting model, the inputs include features related to EV charging habits as well as commonly used weather information. The load forecasting results are evaluated using various metrics, including conventional ones that assess the accuracy of point forecasts, as well as additional metrics that test the reliability of prediction intervals. The proposed load forecasting method is finally tested on real residential power consumption data and EV charging data sampled from real-world sources. Furthermore, the results prove that the new features can greatly improve the performance of the load forecasting method.

• Research Organization: Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
• Sponsoring Organization: USDOE Office of Electricity (OE); USDOE Office of Energy Efficiency and Renewable Energy (EERE), Energy Efficiency Office. Building Technologies Office
• Grant/Contract Number: AC02-05CH11231; AC36-08GO28308
• OSTI ID: 2539844
• Alternate ID(s): OSTI ID: 2500375
• Journal Information: North American Power Symposium, Journal Name: North American Power Symposium Vol. 2024; ISSN 2163-4939
• Publisher: IEEE
• Country of Publication: United States
• Language: English

Related Subjects

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION
Gaussian process regression
electrical vehicle
load forecasting
probabilistic forecasting