Sascha Gohlke

Mr. Sascha Gohlke

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 December 2023 in World Electric Vehicle Journal
Verified
Journal Article
Open access
PDF file
TFTobias Fleck
Tobias Fleck
SGSascha Gohlke
Sascha Gohlke
ZNZoltan Nochta
Zoltan Nochta
Smart charging is a means of monitoring and actively controlling EV chargers to optimize the distribution and consumption of energy with a focus on peak-load avoidance. This paper describes the most important requirements that have influenced the design and implementation of the “Smart Charging System” (SCS). It presents the architecture and main functional building blocks of the SCS, which have been realized in an iterative development process as an extension component of the already existing open-source solution “Open e-Mobility”. We also provide details on the functionality of the core smart charging algorithm within SCS and show how various data sources can be utilized by the system to increase the safety and efficiency of EV charging processes. Furthermore, we describe our iterative approach to developing the system, introduce the real-world testbed at SAP Labs France in Mougins/France, and share evaluation results and experiences gathered over a three-year period.

23 November 2022 in World Electric Vehicle Journal
Verified
Journal Article
Open access
PDF file
JGJoela Gauss
Joela Gauss
SGSascha Gohlke
Sascha Gohlke
ZNZoltan Nochta
Zoltan Nochta
Resource sharing in general is a means of solving the problem of infrequent and, thus, inefficient utilization of expensive or scarce resources. In this paper, we present an approach to run shared EV-charging infrastructures in the context of commercial real-estate facilities. Collaborating EV-charger owners thereby create a pool of chargers for shared use. In our work, we consider aspects of economic viability, desirability and technical feasibility as prerequisites of a successful solution. We formally prove that the basic economic potential of the proposed pooling with regard to overall infrastructure utilization is given. In order to operate the shared pool of charging points at a given location, the corresponding management software must fulfil specific requirements. Our prototype implementation that was realized as an extension of the open-source system Open E-Mobility demonstrates the technical feasibility of the sharing idea in a user-friendly way. Questionnaires and personal interviews conducted with owners of small and medium-sized businesses revealed that they would share charging stations if it helped overcome availability bottlenecks, thus improving customer and employee perception.

30 November 2025 in World Electric Vehicle Journal
Verified
Journal Article
Open access
PDF file
SGSascha Gohlke
Sascha Gohlke
ZNZoltan Nochta
Zoltan Nochta
To operate electric vehicle (EV) fleets in a safe and efficient manner, many companies have been deploying charging infrastructures (CIs) at their premises. Forecasting of different system parameters of a CI, such as how many charging points will be occupied during the day, can help create accurate charge plans. In this paper, we deal with the applicability of continuous Nowcasting, i.e., frequently executed short-term forecasts, to predict the next few data points based on the past and current situation in a CI. Specifically, we forecast the number of charging EVs over a rolling two-hour horizon using XGBoost and LSTM. In the experiments, we apply different weighting schemes to emphasize the relevance of the most recent observations combined with different multi-horizon forecasting strategies. Experimental results using a real-world dataset show that a linear weighting schema combined with a direct forecasting strategy using XGBoost achieves the lowest RMSE value of 0.906 for the 15 min forecasting horizon when predicting the number of active charging stations. For the 2 h horizon, the best RMSE of 2.545 is achieved with XGBoost using the strategy Direct, but with an exponential weighting strategy. We then illustrate how short-term predictions can be used to improve the operational efficiency of an example CI by dynamically adjusting power limits based on the latest prediction results.