Urbanev: An open benchmark dataset for urban electric vehicle charging demand prediction

The recent surge in electric vehicles (EVs), driven by a collective push to enhance global environmental sustainability, has underscored the significance of exploring EV charging prediction. To catalyze further research in this domain, we introduce UrbanEV—an open dataset showcasing EV charging space availability and electricity consumption in a pioneering city for vehicle electrification, namely Shenzhen, China. UrbanEV offers a rich repository of charging data (i.e., charging occupancy, duration, volume, and price) captured at hourly intervals across an extensive six-month span for over 20,000 individual charging stations. Beyond these core attributes, the dataset also encompasses diverse influencing factors like weather conditions and spatial proximity. These factors are thoroughly analyzed qualitatively and quantitatively to reveal their correlations and causal impacts on charging behaviors. Furthermore, comprehensive experiments have been conducted to showcase the predictive capabilities of various models, including statistical, deep learning, and transformer-based approaches, using the UrbanEV dataset. This dataset is poised to propel advancements in EV charging prediction and management, positioning itself as a benchmark resource within this burgeoning field.

Methods
To build a comprehensive and reliable benchmark dataset, we conduct a series of rigorous processes from data collection to dataset evaluation. The overall workflow sequentially includes data acquisition, data processing, statistical analysis, and prediction assessment. As follows, please see detailed descriptions.

Study area and data acquisition

Shenzhen, a pioneering city in global vehicle electrification, has been selected for this study with the objective of offering valuable insights into electric vehicle (EV) development that can serve as a reference for other urban centers. This study encompasses the entire expanse of Shenzhen, where data on public EV charging stations distributed around the city have been meticulously gathered. Specifically, EV charging data was automatically collected from a mobile platform used by EV drivers to locate public charging stations.
Through this platform, users could access real-time information on each charging pile, including its availability (e.g., busy or idle), charging price, and geographic coordinates.
Accordingly, we recorded the charging-related data at five-minute intervals from September 1, 2022, to February 28, 2023. This data collection process was fully digital and did not require manual readings. Furthermore, to delve into the correlation between EV charging patterns and environmental elements, weather data for Shenzhen city were acquired from two meteorological observatories situated in the airport and central regions, respectively. These meteorological data are publicly available on the Shenzhen Government Data Open Platform. Thirdly, point of interest (POI) data was extracted through the Application Programming Interface Platform of AMap.com, along with three primary types: food and beverage services, business and residential, and lifestyle services. Lastly, the spatial and static data were organized based on the traffic zones delineated by the sixth Residential Travel Survey of Shenzhen. The collected data contains detailed spatiotemporal information that can be analyzed to provide valuable insights about urban EV charging patterns and their correlations with meteorological conditions.

Shenzhen, a pioneering city in global vehicle electrification, has been selected for this study with the objective of offering valuable insights into electric vehicle (EV) development that can serve as a reference for other urban centers. This study encompasses the entire expanse of Shenzhen, where data on public EV charging stations distributed around the city have been meticulously gathered. Specifically, a program was employed to extract the status (e.g., busy or idle, charging price, electricity volume, and coordinates) of each charging pile at five-minute intervals from 1 September 2022 to 28 February 2023. Furthermore, to delve into the correlation between EV charging patterns and environmental elements, weather data for Shenzhen city was acquired from two meteorological observatories situated in the airport and central regions, respectively. Thirdly, point of interest (POI) data was extracted, along with three primary types: food and beverage services, business and residential, and lifestyle services. Lastly, the spatial and static data were organized based on the traffic zones delineated by the sixth Residential Travel Survey of Shenzhen. The collected data contains detailed spatiotemporal information that can be analyzed to provide valuable insights about urban EV charging patterns and their correlations with meteorological conditions.

Processing raw information into well-structured data
To streamline the utilization of the UrbanEV dataset, we harmonize heterogeneous data from various sources into well-structured data with aligned temporal and spatial resolutions. This process can be segmented into two parts: the reorganization of EV charging data and the preparation of other influential factors.

EV charging data
The raw charging data, obtained from publicly available EV charging services, pertains to charging stations and predominantly comprises string-type records at a 5-minute interval. To transform this raw data into a structured time series tailored for prediction tasks, we implement the following three key measures:

Initial Extraction. From the string-type records, we extract vital information for each charging pile, such as availability (designated as "busy" or "idle"), rated power, and the corresponding charging and service fees applicable during the observed time periods. First, a charging pile is categorized as "active charging" if its states at two consecutive timestamps are both "busy". Consequently, the occupancy within a charging station can be defined as the count of in-use charging piles, while the charging duration is calculated as the product of the count of in-use piles and the time between the two timestamps (in our case, 5 minutes). Moreover, the charging volume in a station can correspondingly be estimated by multiplying the duration by the piles' rated power. Finally, the average electricity price and service price are calculated for each station in alignment with the same temporal resolution as the three charging variables.

Error Detection and Imputation. Ensuring data quality is paramount when utilizing charging data for decision-making, advanced analytics, and machine-learning applications. It is crucial to address concerns around data cleanliness, as the presence of inaccuracies and inconsistencies, often referred to as dirty data, can significantly compromise the reliability and validity of any subsequent analysis or modeling efforts. To improve data quality of our charging data, several errors are identified, particularly the negative values for charging fees and the inconsistencies between the counts of occupied, idle, and total charging piles. We remove the records containing these anomalies and treat them as missing data. Besides that, a two-step imputation process was implemented to address missing values. First, forward filling replaced missing values using data from preceding timestamps. Then, backward filling was applied to fill gaps at the start of each time series. Moreover, a certain number of outliers were identified in the dataset, which could significantly impact prediction performance. To address this, the interquartile range (IQR) method was used to detect outliers for metrics including charging volume (v), charging duration (d), and the rate of active charging piles at the charging station (o). To retain more original data and minimize the impact of outlier correction on the overall data distribution, we set the coefficient to 4 instead of the default 1.5. Finally, each outlier was replaced by the mean of its adjacent valid values. This preprocessing pipeline transformed the raw data into a structured and analyzable dataset.

Aggregation and Filtration. Building upon the station-level charging data that has been extracted and cleansed, we further organize the data into a region-level dataset with an hourly interval providing a new perspective for EV charging behavior analysis. This is achieved by two major processes: aggregation and filtration. First, we aggregate all the charging data from both temporal and spatial views: a. Temporally, we standardize all time-series data to a common time resolution of one hour, as it serves as the least common denominator among the various resolutions. This aims to establish a unified temporal resolution for all time-series data, including pricing schemes, weather records, and charging data, thereby creating a well-structured dataset.  Aggregation rules specify that the five-minute charging volume v and duration $(d)$ are summed within each interval (i.e., one hour), whereas the occupancy o, electricity price pe, and service price ps are assigned specific values at certain hours for each charging pile. This distinction arises from the inherent nature of these data types: volume v and duration d are cumulative, while o, pe, and ps are instantaneous variables. Compared to using the mean or median values within each interval, selecting the instantaneous values of o, pe, and ps as representatives preserves the original data patterns more effectively and minimizes the influence of human interpretation. b. Spatially, stations are aggregated based on the traffic zones delineated by the sixth Residential Travel Survey of Shenzhen. After aggregation, our aggregated dataset comprises 331 regions (also called traffic zones) with 4344 timestamps. Second, variance tests and zero-value filtering functions were employed to filter out traffic zones with zero or no change in charging data. Specifically, it means that regions with an occupancy variance below 0.001 or a proportion of zero values exceeding 30% were excluded. As a result,  275 traffic zones are ultimately retained, encompassing a total of 1,362 charging stations and 17,532 charging piles, for subsequent usage.

Other influential factors
Apart from the EV charging data, we also constructed a set of variables that might influence charging behaviors. These variables can be categorized into three classes, namely temporal factors, spatial attributes, and static features. First and foremost, the temporal factors include three weather conditions: air temperature (Ta), relative humidity (h), and atmospheric pressure (P). The raw weather data is collected from two meteorological observatories located in the airport and central regions of Shenzhen, and they were further organized into numeric data with the same hourly interval as the structured charging data. Notably, the weather data is shared by all the charging stations or traffic zones. Furthermore, spatial information, such as the adjacency matrix and distances, is computed using ArcGIS tools. Specifically, the adjacency is determined by checking whether two traffic zones have adjacent edges based on the distance calculated from their geometric centers. Lastly, UrbanEV also provides static features including Point of Interest (POI), area, and road length in each traffic zone. Moreover, we filtered and selected only those that are relevant to charging activities within the 275 specific zones aligned with the structured charging data.