This study assesses the performance of a multivariate multi‐step charging load prediction approach based on the long short‐term memory (LSTM) and commercial charging data. The major contribution of this study is to provide a comparison of load prediction between various types of charging sites. Real charging data from shopping centres, residential, public, and workplace charging sites are gathered. Altogether, the data consists of 50,504 charging events measured at 37 different charging sites in Finland between January 2019 and January 2020. A forecast of the aggregated charging load is performed in 15‐min resolution for each type of charging site. The second contribution of the work is the extended short‐term forecast horizon. A multi‐step prediction of either four (i.e., one hour) or 96 (i.e., 24 h) time steps is carried out, enabling a comparison of both horizons. The findings reveal that all charging sites exhibit distinct charging characteristics, which affects the forecasting accuracy and suggests a differentiated analysis of the different charging categories. Furthermore, the results indicate that the forecasting accuracy strongly correlates with the forecast horizon. The 4‐time step prediction yields considerably superior results compared with the 96‐time step forecast.

There is a general interest from manufacturers, users, regulation institutions, and research around electric vehicles development and its relation with the grid infrastructure. The penetration of electric vehicles in distribution networks brings considerable challenges in terms of power quality, particularly harmonic emissions. Such challenges are more evident in scenarios with high penetration of electric vehicles which consider the clustering effect in the charging process. Methodologies such as hosting capacity model electric vehicles as a constant power load with constant harmonic distortion along the entire charging process. This article presents the relationship between the charging algorithms of the electric vehicle chargers, the state of charge of the batteries, and the harmonic current distortion generated during the charging process. This model proposes that the harmonic current distortion depends on the state of charge of the battery and the charging algorithm of the vehicle. As this study would change meaningfully, the current studies of power quality related to electric vehicles, practical measurements in two charging stations, and offline simulations of the identified on-board chargers are shown to support the content of this article.

The phase voltages of a series-connected H-bridge multilevel inverter are formed from galvanically isolated secondaries of complicated transformer. The reactive energy of a reactive load flowing back to the DC links is not transferred to other phases the same way as is in two-level inverters. Therefore the DC link voltages in multilevel inverters fluctuate under load and cannot be considered constant. Voltage fluctuation causes several problems including erroneous voltage vector production and undesired harmonics to voltage and current. A simple compensation method for such a DC link voltage fluctuation in series-connected multilevel inverters is proposed. The method is shown to be applicable to both space vector modulation and duty-cycle modulation schemes. The algorithm also includes circulation of the modules to ensure equal loading of different DC links. The proposed method was simulated using the parameters of a 3 kV three-phase seven-level inverter. Laboratory measurements with a 100 kVA inverter also verify the operation. The simulations and test results show the algorithm to fix unideal voltages to correspond the demanded reference. Also DC link voltages remain very well in balance, because of the use of module circulation.

The number of electric vehicle (EV) users is strongly increasing so that today roughly every second registered vehicle in Norway is an EV. To increase the EV utilization, politics, industry and the EV users strongly promote the integration of fast charging infrastructure. While the future demand of fast charging sites is a well‐studied topic, not much is known about the utilization of the existing charging sites and daily load curves. To fill this knowledge gap, usage data of a charging site in Oslo is analysed. Further on, the impact of a battery energy storage (BES) as well as a photovoltaic generator on peak load reduction is studied. The analysis shows variations and trends in the daily and weekly charging behaviour depending on the degree of utilization of the charging station. On average, a single EV user charges around 10 kWh in 19 min. Furthermore, the evidence indicates that EV users may have adapted fast charging as a part of their daily travels and it is not used only during long distance journeys. The results suggest that a BES can reduce the peak load by up to 55%. By adding a photovoltaic generator, a minor additional reduction of peak load is seen.

The inconvenient nature of non‐ideal charging characteristics is demonstrated from a power system point of view. A new adaptive charging algorithm that accounts for non‐ideal charging characteristics is introduced. The proposed algorithm increases the local network capacity utilization rate and reduces charging times. The first unique element of the charging algorithm is exploitation of the measured charging currents instead of ideal or predefined values. The second novelty is the introduction of a short‐term memory called expected charging currents. This makes the algorithm capable of adapting to the unique charging characteristics of each vehicle individually without the necessity to obtain any information from the vehicle or the user. The proposed algorithm caters to various non‐idealities, such as phase unbalances or the offset between the current set point and the real charging current but is still relatively simple and computationally light. The algorithm is compatible with charging standard IEC 61851 and is validated under different test cases with commercial electric vehicles.