Vehicle Charging Load Research Articles

Electric Vehicle Charging Load Demand Forecasting in Different Functional Areas of Cities with Weighted Measurement Fusion UKF Algorithm

The forecasting of charging demand for electric vehicles (EVs) plays a vital role in maintaining grid stability and optimizing energy distribution. Therefore, an innovative method for the prediction of EV charging load demand is proposed in this study to address the downside of the existing techniques in capturing the spatial–temporal heterogeneity of electric vehicle (EV) charging loads and predicting the charging demand of electric vehicles. Additionally, an innovative method of electric vehicle charging load demand forecasting is proposed, which is based on the weighted measurement fusion unscented Kalman filter (UKF) algorithm, to improve the accuracy and efficiency of forecasting. First, the data collected from OpenStreetMap and Amap are used to analyze the distribution of urban point-of-interest (POI), to accurately classify the functional areas of the city, and to determine the distribution of the urban road network, laying a foundation for modeling. Second, the travel chain theory was applied to thoroughly analyze the travel characteristics of EV users. The Improved Floyd (IFloyd) algorithm is used to determine the optimal route. Also, a Monte Carlo simulation is performed to estimate the charging load for electric vehicle users in a specific region. Then, a weighted measurement fusion UKF (WMF–UKF) state estimator is introduced to enhance the accuracy of prediction, which effectively integrates multi-source data and enables a more detailed prediction of the spatial–temporal distribution of load demand. Finally, the proposed method is validated comparatively against traffic survey data and the existing methods by conducting a simulation experiment in an urban area. The results show that the method proposed in this paper is applicable to predict the peak hours more accurately compared to the reference method, with the accuracy of first peak prediction improved by 53.53% and that of second peak prediction improved by 23.23%. The results not only demonstrate the high performance of the WMF–UKF prediction model in forecasting peak periods but also underscore its potential in supporting grid operations and management, which provides a new solution to improving the accuracy of EV load demand forecasting.

Research on Machine Learning-Based Method for Predicting Industrial Park Electric Vehicle Charging Load

To achieve global sustainability goals and meet the urgent demands of carbon neutrality, China is continuously transforming its energy structure. In this process, electric vehicles (EVs) are playing an increasingly important role in energy transition and have become one of the primary user groups in the electricity market. Traditional load prediction algorithms have difficulty in constructing mathematical models for predicting the charging load of electric vehicles, which is characterized by high randomness, high volatility, and high spatial heterogeneity. Moreover, the predicted results often exhibit a certain degree of lag. Therefore, this study approaches the analysis from two perspectives: the overall industrial park and individual charging stations. By analyzing specific load data, the overall framework for the training dataset was established. Additionally, based on the evaluation system proposed in this study and utilizing both Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM) algorithms, a framework for machine learning-based load prediction methods was constructed to forecast electric vehicle charging loads in industrial parks. Through a case analysis, it was found that the proposed solution for the short-term prediction of the charging load in industrial park electric vehicles can achieve accurate and stable forecasting results. Specifically, in terms of data prediction for normal working days and statutory holidays, the Long Short-Term Memory (LSTM) algorithm demonstrated high accuracy, with R2 coefficients of 0.9283 and 0.9154, respectively, indicating the good interpretability of the model. In terms of weekend holiday data prediction, the Multilayer Perceptron (MLP) algorithm achieved an R2 coefficient of as high as 0.9586, significantly surpassing the LSTM algorithm’s value of 0.9415, demonstrating superior performance.

A novel framework for assessing the smartness and the smart readiness level in highly electrified non-residential buildings: A Norwegian case study

This work presents a new operational framework to measure the smartness and smart readiness of highly electrified buildings. The framework seeks to enhance legacy systems and controls of existing buildings and establish minimum criteria for future constructions to ensure they interact effectively with users and the grid, aiming for a clean energy transition. To this end, we develop two modified complementary assessments, one based on the method indicated by the Smart Readiness Indicator (SRI), proposed by the European Union (EU), and the other following the Smart by Powerhouse scheme, introduced by a Norwegian consortium of stakeholders focused on developing future proof climate buildings. The proposed structure is implemented in ten non-residential buildings in Norway with different energy systems, typologies, and construction dates. The results of this study demonstrate that energy flexibility quantification plays a crucial role in correctly implementing the framework in highly electrified buildings. Therefore, the dynamic impact of having Electric Vehicle Charging (EVC) and other electrical-dependent loads must be considered in the assessment. With the proposed modifications, the EVC weight in the flexibility score now varies from 24.0 to 43.6%, up from the original 5%. Overall, the pilot buildings have a smart readiness level between 21.6% and 31.7%, with mostly automated smartness levels. Nevertheless, the study also emphasizes the need to differentiate current HVAC (Heating, Ventilation, and Air Conditioning) technologies and their efficiencies.

Block-FeDL: Electric Vehicle Charging Load Forecasting using Federated Learning and Blockchain

Block-FeDL: Electric Vehicle Charging Load Forecasting using Federated Learning and Blockchain

Electric Vehicle Charging Load Optimization Strategy Based on Dynamic Time-of-Use Tariff

Electric Vehicle Charging Load Optimization Strategy Based on Dynamic Time-of-Use Tariff

Count the charging load forecast of the battery remaining life and ownership

In order to solve the accuracy of EV charging load prediction, the residual life reduction and the exact value of EV ownership caused by battery aging are taken into consideration. The charging load curve of the EV is simulated based on the Monte Carlo simulation method. Finally, based on the actual data of a certain region, the charging load of electric vehicles within a day is obtained. The case analysis shows that the proposed charging load prediction model of electric vehicles has high accuracy, which also shows that the large-scale grid connection of electric vehicles will bring new challenges to the power system. This method provides data support for the subsequent formulation of electric vehicle charging strategy and load side peak shifting and valley filling.

Power Measurement Using Adaptive Chirp Mode Decomposition for Electrical Vehicle Charging Load

Due to nonlinear components in the charging piles of electric vehicles, harmonics and nonstationary signals in the electric vehicle charging load bring voltage and current distortion, seriously affecting the accuracy of the power-related calculation in nonsinusoidal environments. This paper proposed a new approach to calculate the active power and root mean square values from decomposed components using the adaptive chirp mode decomposition (ACMD) method on voltage and current. The advantage of the ACMD-based method is that it correctly provides the power-related quantities of harmonics or nonstationary components for the electric vehicle charging load. The performance of the proposed method was verified using synthetic signals and simulation tests. The experimental results presented better estimations for each quantity defined in IEEE Standard 1459-2010, compared with the discrete wavelet transform approach.

Research on electric vehicle charging load based on the monte Carlo

With the increasing number of electric cars, they may become the most important load in the grid of the future. Due to the randomness of electric vehicles access to the grid, when large-scale electric vehicles are linked to the grid, they will fluctuate on the grid, resulting in the failure of the power supply mode and operation control means of the traditional distribution network to attain the optimal result. In view of this phenomenon, based on the Monte Carlo calculation and simulation, the charging load of electric vehicles is predicted, which can achieve comprehensive prediction under different kinds of electric cars, different battery capacities, different charging methods, etc, and provide theoretical and technical support for the effect analysis of electric vehicles access to power grid.

Electric Vehicle Charging Load Demand Forecasting Model based on Spatial and Temporal Characteristics

This paper proposes a method to predict the charging load demand of electric vehicles considering the spatial and temporal distribution characteristics of users’ travel. Based on the central limit theorem and travel chain theory, the temporal distribution of the charging load of different functional sites is simulated by the Monte Carlo method and calculated by combining NHTS2017 data to find the total daily charging load of electric private vehicles. The results show that in the case of disorderly charging, the charging loads of different areas have more obvious temporal characteristics, and the charging service can be optimized according to this charging load characteristic.

A novel AC-DC hybrid microgrid architecture and control strategy for electric vehicle swap station

The characteristics of small volume, modularity, and easy expansion in solid-state transformers (SST), which makes SST widely applied in electric vehicle swapping stations. However, due to various loads and pulsed loads, voltage instability and fluctuation problems inevitably occur in electric vehicle swapping stations. Aiming at these problems, a topology structure based on a Modular Multilevel Solid State Transformer (MMC-SST) is proposed. It is the first choice for realizing the flexible power allocation of AC/DC hybrid system and the interconnection of medium and low voltage. The performance of the DC bus voltage of the charging station has been improved. Based on this topology, an energy management strategy with virtual synchronous generator (VSG) control is proposed to smoothly transition the on-grid and off-grid processes of the distributed power source. In addition, due to the frequency regulation is applied in the control system, the energy storage system has damping and inertia when the output of the new energy power generation equipment changes or load fluctuation, reducing the impact on the load energy storage equipment and improving the stability and safety of the electric vehicle charging station system. Finally, the effectiveness of the proposed topology and its control strategy in different working scenarios are verified by simulation. Simulation analysis shows that the proposed topology has good advantages in DC bus voltage stability, optimization of electric vehicle charging characteristics and load management.

Probabilistic Load Flow of an Islanded Microgrid with WTGS and PV Uncertainties Containing Electric Vehicle Charging Loads

With the emphasis of utilities on decentralized power systems due to the considerable growth of renewable energy resources (RES), microgrids (MGs) as controllable small grids are need of an hour. For an objective analysis of microgrids with large grid parity of renewable energy sources, probabilistic methods are required along with the already established deterministic methods. A Gauss quadrature-based probabilistic load flow (GQPLF) method for microgrid has been proposed along with intermittent generation and uncertain loads, including electric vehicles (EVs). The distributed generation consists of wind turbine generation systems (WTGS) and photovoltaic systems (PVs) connected to 14 bus microgrid systems with six droop-controlled distributed generators. Extensive simulations have been carried out on a 14-bus microgrid with distributed generation and uncertain loads, and results are compared with the benchmark Monte Carlo simulation (MCS) method, which validates the efficacy of the proposed method. The time taken by the proposed GQPLF for the 14-bus microgrid system simulation is 60.9 seconds, which is significantly less compared to the benchmark Monte Carlo simulation method, in which time taken for a 14-bus microgrid system with 10,000 simulations is 9318.7 seconds. Comparing the proposed GQPLF method with the benchmark method validates its efficacy and efficiency.

Comparative Analysis of Deep Learning Models for Electric Vehicle Charging Load Forecasting

Comparative Analysis of Deep Learning Models for Electric Vehicle Charging Load Forecasting

Electric vehicle charging load prediction considering the orderly charging

The prediction of the orderly charging load of electric vehicles is of great significance for planning of charging facilities, analysis of bearing capacity of the distribution network and later rectification and reconstruction. This article proposes a method of charging load prediction based on characteristics of EV charging behavior and nonlinear programming. This article uses Monte Carlo algorithm to predict charging probability and disorderly charging load of EVs, and uses non -linear programming algorithm to solve the optimized target function of orderly charging to achieve the prediction of the orderly charging load of EVs in the region.

Optimal design and energy management of residential prosumer community with photovoltaic power generation and storage for electric vehicles

The optimum design and management of residential photovoltaic (PV) communities are essential to the reliability to satisfy the demands of communities due to the volatility and intermittence of solar energy. The retailer for energy dispatch management is introduced to improve the economic performances of PV communities through demand-side management measures with the electric grid. This paper proposes a novel two-stage optimization model of design and electricity dispatch strategies for residential PV communities to operate electric vehicles' charges. The first-stage optimization aims to obtain the optimal capacities of PV and batteries. The second-stage optimization optimizes the retailer's hourly electricity prices and electricity dispatch strategies, in which the Stackelberg game is performed between maximizing the retailer's benefit and minimizing the electricity cost of residential basic loads and vehicle charging loads. A case study is implemented to validate the proposed model. The installation capacity of batteries is appropriately increased with the increasing active loads of electric vehicles. The optimal pricing strategies of the retailer based on the trade schemes with the electricity grid are influenced by their ratios of fixed and active loads. Compared to the community without the retailer, the annual electricity cost of users is saved by 21.2 % through the proposed management strategy.

Optimal Configuration of Hybrid AC/DC Distribution Network Considering the Temporal Power Flow Complementarity on Lines

To mitigate the voltage violation and overloading caused by the integration of Distributed Generation (DG) and Electric Vehicle Charging (EVC) loads, a feasible solution is to convert some AC medium voltage distribution lines to DC ones and formulate an AC/DC hybrid distribution network, based on which flexible power shifting between lines can be achieved. However, the complementarity of power flows amongst AC/DC lines is hardly described and embedded in existing configuration optimization methods in which only the average loading or the variations of loading for a certain period is considered. Solution space will be geometrically increased if operation scenarios are fully simulated for configuration caused by the strong uncertainties of DGs and EVC loads. This paper proposes an analytic quantifiable method to describe the power complementarity between AC/DC lines. The Gaussian mixture model is used to depict the temporal correlation and uncertainties. The complementarity is calculated by the conditional probability of multi-dimensional joint probability density function of AC/DC hybrid lines. Accordingly, an optimal configuration method of hybrid AC/DC distribution network is proposed considering the complementarity of power flows on AC/DC lines, in which the size and location of Voltage Source Converters (VSCs) are optimized. Simulations studies are performed to verify the proposed method.

Dynamic Load Prediction Model of Electric Bus Charging Based on WNN

Electric buses have a significant penetration rate and high charging frequency and amount. Therefore, their charging load has a momentous influence on the power grid’s operation and dispatch. There are important theoretical and practical reasons to study electric bus charging load prediction; however, the intermittent and random charging behavior of buses makes it more difficult to predict charging load predictions, particularly, in real time. To accomplish this, in this paper a WNN (wavelet neural network)-based dynamic load prediction model for charging electric buses is suggested. We start by using distance and shape to group the charging load curve which, in fact, is done with spectral clustering. As a second step, we take into account a wide range of charging load-affecting variables such as temperature and time of day, in order to better train the WNN. Moreover, the charge loads for each cluster are predicted based on model parameters; subsequently, the forecast day’s total charging load is then calculated by summing the prediction results for each cluster; finally, the proposed method is validated using a real city data set. In our empirical evaluation, it has been found that, under various indicators, the proposed method’s ability to precisely forecast the charging load of electric vehicles has significantly improved. In fact, this allows for better guidance of charging user, planning, and expanding the power grid in consideration of electric vehicle charging loads.

Situation Awareness of Electric Vehicle Charging Load Based on Random Forest Algorithm

Due to the important characteristics of energy saving and carbon reduction, electric vehicles have attracted worldwide attention. It can be predicted that the power grid will be faced with the access problem of large-scale electric vehicles. In order to master the user behavior characteristics of electric vehicle load, it is necessary to establish the model based on electric vehicle charging behavior. In this paper, combined with the electric vehicle charging demand and the situational awareness results of the dispatchable resources in the station area, the characteristic indicators of the electric vehicle load are quantitatively analyzed. Situational prediction of electric vehicle load based on random forest algorithm is proposed, and the sample set is divided and trained. A simulation example is used to verify the effectiveness of the method provided in load forecasting.

Short-Term Load Forecasting Model of Electric Vehicle Charging Load Based on MCCNN-TCN

The large fluctuations in charging loads of electric vehicles (EVs) make short-term forecasting challenging. In order to improve the short-term load forecasting performance of EV charging load, a corresponding model-based multi-channel convolutional neural network and temporal convolutional network (MCCNN-TCN) are proposed. The multi-channel convolutional neural network (MCCNN) can extract the fluctuation characteristics of EV charging load at various time scales, while the temporal convolutional network (TCN) can build a time-series dependence between the fluctuation characteristics and the forecasted load. In addition, an additional BP network maps the selected meteorological and date features into a high-dimensional feature vector, which is spliced with the output of the TCN. According to experimental results employing urban charging station load data from a city in northern China, the proposed model is more accurate than artificial neural network (ANN), long short-term memory (LSTM), convolutional neural networks and long short-term memory (CNN-LSTM), and TCN models. The MCCNN-TCN model outperforms the ANN, LSTM, CNN-LSTM, and TCN by 14.09%, 25.13%, 27.32%, and 4.48%, respectively, in terms of the mean absolute percentage error.

Electric Vehicle Charging Load Allocation at Residential Locations Utilizing the Energy Savings Gained by Optimal Network Reconductoring

In this study, a two-stage methodology based on the energy savings gained by optimal network reconductoring was developed for the sizing and allocation of electric vehicle (EV) charging load at the residential locations in urban distribution systems. During the first stage, the Flower Pollination Algorithm (FPA) was applied to minimize the annual energy losses of the radial distribution system through optimum network reconductoring. A multi-objective function was formulated to minimize investment, peak loss, and annual energy loss costs at different load factors. The results obtained with the flower pollination algorithm were compared with the particle swarm optimization algorithm. In the second stage, a simple heuristic procedure was developed for the sizing and allocation of EV charging load at every node of the distribution system utilizing part of the annual energy savings obtained by optimal network reconductoring. The number of electric cars, electric bikes, and electric scooters that can be charged at every node was computed while maintaining the voltage and branch current constraints. The simulation results were demonstrated on 123 bus and 51 bus radial distribution networks to validate the effectiveness of the proposed methodology.

Multinodes Interval Electric Vehicle Charging Load Forecasting Based on Joint Adversarial Generation

Multinodes Interval Electric Vehicle Charging Load Forecasting Based on Joint Adversarial Generation