A Novel Ultra Short-Term Load Forecasting Method for Regional Electric Vehicle Charging Load Using Charging Pile Usage Degree

Electric vehicle(EV)charging load is greatly affected by many traffic factors,such as road congestion.Accurate ultra short-term load forecasting(STLF)results for regional EV charging load are important to the scheduling plan of regional charging load,which can be derived to realize the optimal vehicle to grid benefit.In this paper,a regional-level EV ultra STLF method is proposed and discussed.The usage degree of all charging piles is firstly defined by us based on the usage frequency of charging piles,and then constructed by our collected EV charging transactiondata in thefield.Secondly,these usagedegrees are combinedwithhistorical charging loadvalues toform the inputmatrix for the deep learning based load predictionmodel.Finally,long short-termmemory(LSTM)neural network is used to construct EV charging load forecastingmodel,which is trained by the formed inputmatrix.The comparison experiment proves that the proposed method in this paper has higher prediction accuracy compared with traditionalmethods.In addition,load characteristic index for the fluctuation of adjacent day load and adjacent week load are proposed by us,and these fluctuation factors are used to assess the prediction accuracy of the EV charging load,together with the mean absolute percentage error(MAPE).

EV Charging Station Load Prediction in Coupled Urban Transportation and Distribution Networks

The increasingly large number of electric vehicles(EVs)has resulted in a growing concern for EV charging station load prediction for the purpose of comprehensively evaluating the influence of the charging load on distribution networks.To address this issue,an EV charging station load predictionmethod is proposed in coupled urban transportation and distribution networks.Firstly,a finer dynamic urban transportation network model is formulated considering both nodal and path resistance.Then,a finer EV power consumption model is proposed by considering the influence of traffic congestion and ambient temperature.Thirdly,the Monte Carlo method is applied to predict the distribution of EVcharging station load based on the proposed dynamic urban transportation network model and finer EV power consumption model.Moreover,a dynamic charging pricing scheme for EVs is devised based on the EV charging station load requirements and the maximum thresholds to ensure the security operation of distribution networks.Finally,the validity of the proposed dynamic urban transportation model was verified by accurately estimating five sets of test data on travel time by contrast with the BPR model.The five groups of travel time prediction results showed that the average absolute percentage errors could be improved from 32.87%to 37.21%compared to the BPR model.Additionally,the effectiveness of the proposed EV charging station load prediction method was demonstrated by four case studies in which the prediction of EV charging load was improved from27.2 to 31.49MWh by considering the influence of ambient temperature and speed on power energy consumption.

Charging load prediction method for expressway electric vehicles considering dynamic battery state-of-charge and user decision

Accurate prediction of electric vehicle(EV)charging loads is a foundational step in the establishment of expressway charging infrastructures.This study introduces an approach to enhance the precision of expressway EV charging load predictions.The method considers both the battery dynamic state-of-charge(SOC)and user charging decisions.Expressway network nodes were first extracted using the open Gaode Map API to establish a model that incorporates the expressway network and traffic flow fea-tures.A Gaussian mixture model is then employed to construct a SOC distribution model for mixed traffic flow.An innovative SOC dynamic translation model is then introduced to capture the dynamic characteristics of traffic flow SOC values.Based on this foun-dation,an EV charging decision model was developed which considers expressway node distinctions.EV travel characteristics are extracted from the NHTS2017 datasets to assist in constructing the model.Differentiated decision-making is achieved by utilizing improved Lognormal and Sigmoid functions.Finally,the proposed method is applied to a case study of the Lian-Huo expressway.An analysis of EV charging power converges with historical data and shows that the method accurately predicts the charging loads of EVs on expressways,thus revealing the efficacy of the proposed approach in predicting EV charging dynamics under expressway scenarios.

Electric Vehicle Charging Capacity of Distribution Network Considering Conventional Load Composition

At present,the large-scale access to electric vehicles(EVs)is exerting considerable pressure on the distribution network.Hence,it is particularly important to analyze the capacity of the distribution network to accommodate EVs.To this end,we propose a method for analyzing the EV capacity of the distribution network by considering the composition of the conventional load.First,the analysis and pretreatment methods for the distribution network architecture and conventional load are proposed.Second,the charging behavior of an EVis simulated by combining the Monte Carlo method and the trip chain theory.After obtaining the temporal and spatial distribution of the EV charging load,themethod of distribution according to the proportion of the same type of conventional load among the nodes is adopted to integrate the EV charging load with the conventional load of the distribution network.By adjusting the EV ownership,the EV capacity in the distribution network is analyzed and solved on the basis of the following indices:node voltage,branch current,and transformer capacity.Finally,by considering the 10-kV distribution network in some areas of an actual city as an example,we show that the proposed analysis method can obtain a more reasonable number of EVs to be accommodated in the distribution network.

Procedural simulation method for aggregating charging load model of private electric vehicle cluster

The usage of each private electric vehicle(PrEV)is a repeating behavior process composed by driving,parking,discharging and charging,in which PrEV shows obvious procedural characteristics.To analyze the procedural characteristics,this paper proposes a procedural simulation method.The method aggregates the behavior process regularity of the PrEV cluster to model the cluster’s charging load.Firstly,the basic behavior process of each PrEV is constructed by referring the statistical datasets of the traditional private non-electric vehicles.Secondly,all the basic processes are set as a simulation starting point,and they are dynamically reconstructed by several constraints.The simulation continues until the steady state of charge(SOC)distribution and behavior regularity of the PrEV cluster are obtained.Lastly,based on the obtained SOC and behavior regularity information,the PrEV cluster’s behavior processes are simulated again to make the aggregating charging load model available.Examples for several scenarios show that the proposed method can improve the reliability of modeling by grasping the PrEV cluster’s procedural characteristics.

Spatial-temporal Dynamic Forecasting of EVs Charging Load Based on DCC-2D

The charging load of electric vehicles(EVs)has a strong spatiotemporal randomness.Predicting the dynamic spatiotemporal distribution of the charging load of EVs is of great significance for the grid to cope with the access of large-scale EVs.Existing studies lack a prediction model that can accurately describe the dual dynamic changes of EVs charging the load time and space.Therefore,a spatial-temporal dynamic load forecasting model,dilated causal convolution-2D neural network(DCC-2D),is proposed.First,a hole factor is added to the time dimension of the three-dimensional convolutional convolution kernel to form a two-dimensional hole convolution layer so that the model can learn the spatial dimension information.The entire network is then formed by stacking the layers,ensuring that the network can accept long-term historical input,enabling the model to learn time dimension information.The model is simulated with the actual data of the charging pile load in a certain area and compared with the ConvLSTM model.The results prove the validity of the proposed prediction model.

Effect of Hydrogen Charging on the Tensile and Constant Load Properties of an Austenitic Stainless Steel Weldment

The effect of cathodic hydrogen charging on the tensile and constant load properties was deter- mined for an austenitic stainless steel weldment comprising a 304L steel in the solution treated condition as a base metal and a 308L filler steel as a weld metal. Part of the 304L solution treated steel was separately given additional sensitization treatment to simulate the microstructure that would develop in the heat affected zone. Tests were performed at room temperature on notched round bar specimens. Hydrogen charging resulted in a pronounced embrittlement of the tested materials. This was manifested mainly as a considerable loss in the ductility of tensile specimens and a decrease in the time to failure and threshold stress of constant load specimens. The 308L weld metal exhibited the highest, and the 304L solution treated steel the lowest, resistance to hydrogen embrittlement. Hydrogen embrittlement was associated with the formation of strain induced martensite as well as a transition from brittle to ductile fracture morphology onwards the centre of the specimens.

Electric Vehicle Charging Situation Awareness for Ultra-Short-Term Load Forecast of Charging Stations

Electric vehicles(EVs)are expected to be key nodes connecting transportation-electricity-communication networks.Advanced automotive electronics technologies enhance EVs’perception,computing,and communication capacity,which in turn can boost the operational efficiency of intelligent transportation systems(ITSs).EVs couple the ITS to the power system,providing a promising solution to charging congestion and transformer overload via navigation and forecasting approaches.This study proposes a privacy-preserving EV charging situation awareness framework and method to forecast the ultra-short-term load of charging stations.The proposed method only relies on public information from commercial service providers.In the case study,data are powered by the Baidu LBS cloud and EV-SGCC platform,and the experiment is conducted within an area of Pudong New District in Shanghai.Based on the results,the charging load of charging stations can be adequately forecasted more than 1 min ahead with low communication and computing power requirements.This research provides the basis for further studies on operation optimization and electricity market transaction of charging stations.

Data-driven Reliability Assessment of an Electric Vehicle Penetrated Grid Utilizing the Diffusion Estimator and Slice Sampling

Due to the stochasticity of charging behaviors of electric vehicles(EVs),it is difficult to anticipate when charging load demand will be densely concentrated.If massive charging loads and the system peak profile appear at the same time,it may pose a risk to the reliable operation of power grids.For a system integrated with renewable energies,this risk can be much higher because of their unsteady power output.With load measurements more widely collected,this paper presents a data-driven framework to assess the reliability of a power grid considering charging EVs.Specifically,the diffusion estimator is firstly applied to estimate the probability density function of EV charging loads,which possesses both regional adaptivity and good boundary estimation performance.Then,charging load samples are produced through slice sampling.It is capable of sampling from irregularly-shaped distributions with high accuracy.The proposed approach is verified by the numerical results from the simulations on a modified IEEE 30-bus test system based on real measurement data.