1 option
The Prediction for Adjustable Ability of Electric Vehicle Aggregator Based on Deep-Belief-Network Tongji University
- Format:
- Book
- Conference/Event
- Author/Creator:
- Li, Bo, author.
- Conference Name:
- WCX SAE World Congress Experience (2023-04-18 : Detroit, Michigan, United States)
- Language:
- English
- Physical Description:
- 1 online resource cm
- Place of Publication:
- Warrendale, PA SAE International 2023
- Summary:
- In recent years, one of the keys to achieving energy conservation and emission reduction and practicing sustainable development strategies is the wide-area access of large-scale electric vehicles. The charging behavior of large-scale electric vehicles has brought great challenges to the load management and adjustment capacity determination of the power system. Therefore, the prediction of adjustable ability of electric vehicle aggregator based on deep-belief-network is proposed in this paper. First of all, this paper selects the indicators related to the load of the electric bus station: including the arrival time, departure time, and daily mileage of the electric vehicle, from which the SOC variation trend and accurate charging demand of the single electric vehicle are obtained. Secondly, a deep belief network model for load forecasting is established, and the corresponding data set is extracted using historical data, and is used as input together with the load data of electric vehicle aggregators, so as to accurately predict the load situation of electric vehicle aggregators in the next 1 day. Finally, based on the prediction results, the schedulable capacity of the electric vehicle aggregator is obtained. The calculation example shows that the electric vehicle aggregator has a large and stable dispatchable capacity at night. During the day, the user behavior can affect the dispatchable capacity of the aggregator by affecting the state of charge of the electric vehicle. It can be seen that the proposed prediction model has high accuracy and comprehensive consideration
- Notes:
- Vendor supplied data
- Publisher Number:
- 2023-01-0062
- Access Restriction:
- Restricted for use by site license
The Penn Libraries is committed to describing library materials using current, accurate, and responsible language. If you discover outdated or inaccurate language, please fill out this feedback form to report it and suggest alternative language.