Search

Solar photovoltaic (PV) generation is a cornerstone of sustainable energy production, but predicting its capacity across countries remains challenging due to factors like climate, terrain, and population density. To address this, a recent study proposed a novel approach using transfer learning, which is particularly valuable when historical data for newly established PV plants is limited. The study evaluated four PV plants in South Korea and Germany, selected for their diverse geographical and climatic conditions. The proposed CL-Transformer model outperformed established machine learning models such as LSTM, CNN-LSTM, and Transformer, consistently demonstrating superior predictive capabilities. Notably, when trained on Korean data and applied to both South Korea and Germany, the model achieved an average R $^{2}_{\mathrm {adj}}$ improvement of 23.5 %. When trained on German data, the improvement was even more pronounced at 67.3 %. Additionally, transfer learning experiments revealed up to a 50.6 % enhancement in R $^{2}_{\mathrm {adj}}$ across different plant scales. By integrating external weather variables and satellite data, this hybrid model provides valuable insights for accurate capacity prediction and strategic planning in deploying new PV plants, contributing to greater stability and efficiency in the power industry.

Given the inherent fluctuation of photovoltaic (PV) generation, accurately forecasting solar power output and grid feed-in is crucial for optimizing grid operations. Data-driven methods facilitate efficient supply and demand management in smart grids, but predicting solar power remains challenging due to weather dependence and data privacy restrictions. Traditional deep learning (DL) approaches require access to centralized training data, leading to security and privacy risks. To navigate these challenges, this study utilizes federated learning (FL) to forecast feed-in power for the low-voltage grid. We propose a bottom-up, privacy-preserving prediction method using differential privacy (DP) to enhance data privacy for energy analytics on the customer side. This study aims at proving the viability of an enhanced FL approach by employing three years of meter data from three residential PV systems installed in a southern city of Germany, incorporating irradiance weather data for accurate PV power generation predictions. For the experiments, the DL models long short-term memory (LSTM) and gated recurrent unit (GRU) are federated and integrated with DP. Consequently, federated LSTM and GRU models are compared with centralized and local baseline models using rolling 5-fold cross-validation to evaluate their respective performances. By leveraging advanced FL algorithms such as FedYogi and FedAdam, we propose a method that not only predicts sequential energy data with high accuracy, achieving an R2 of 97.68%, but also adheres to stringent privacy standards, offering a scalable solution for the challenges of smart grids analytics, thus clearly showing that the proposed approach is promising and worth being pursued further.

Modern smart grids typically combine physical and communication networks for efficient information exchange and innovative applications. Aligned with digitalization and advancements in smart grids, the integration of photovoltaic (PV) systems comprises a variety of regulatory and technological aspects. However, no previous study has conducted an extensive and systematic analysis of the PV-grid integration framework, particularly for one country. To fill this gap, this paper uses Germany as an example to present a comprehensive, state-of-the-art analysis of integrating distributed PV systems into smart grids, focusing on the regulation and technical implementation of the German Smart Meter Infrastructure and PV control interfaces. Starting from a standardization perspective, this analysis utilizes the Smart Grid Architecture Model to identify crucial roles, components and processes specifically in Germany. Furthermore, it outlines the current implementation of PV integration into distribution networks at a national level. The results of this study show the overall complexity of PV integration in the smart grid context, confirm the feasibility of the German integration approach, and highlight the necessity of deploying standardized information models and communication technologies. These key findings can help market participants with different roles to identify potential technical bottlenecks or other critical points in the regulation and technical implementation. For instance, the proposed in-depth analysis framework provides an orientation for characterizing the PV integration or, more generally, the grid integration scenario of renewables in other countries.

Background and purpose: Active breathing motion management in radiotherapy consists of motion monitoring, quantification and mitigation. It is impacted by associated latencies of a few 100 ms. Artificial neural networks can successfully predict breathing motion and eliminate latencies. However, they require usually a large dataset for training. The objective of this work was to demonstrate that explicitly encoding the cyclic nature of the breathing signal into the training data enables significant reduction of training datasets which can be obtained from healthy volunteers. Material and methods: Seventy surface scanner breathing signals from 25 healthy volunteers in anterior-posterior direction were used for training and validation (ratio 4:1) of long short-term memory models. The model performance was compared to a model using decomposition into phase, amplitude and a time-dependent baseline. Testing of the models was performed on 55 independent breathing signals in anterior-posterior direction from surface scanner (35 lung, 20 liver) of 30 patients with a mean breathing amplitude of (5.9 ± 6.7) mm. Results: Using the decomposed breathing signal allowed for a reduction of the absolute root-mean square error (RMSE) from 0.34 mm to 0.12 mm during validation. Testing using patient data yielded an average absolute RMSE of the breathing signal of (0.16 ± 0.11) mm with a prediction horizon of 500 ms. Conclusion: It was demonstrated that a motion prediction model can be trained with less than 100 datasets of healthy volunteers if breathing cycle parameters are considered. Applied to 55 patients, the model predicted breathing motion with a high accuracy.

To further personalise treatment in metastatic cancer, the indications for metastases-directed local therapy (MDT) and the biology of oligometastatic disease (OMD) should be kept conceptually apart. Both need to be vigorously investigated. Tumour growth dynamics – growth rate combined with metastatic seeding efficiency – is the single most important biological feature determining the likelihood of success of MDT in an individual patient, which might even be beneficial in slowly developing polymetastatic disease. This can be reasonably well assessed using appropriate clinical imaging. In the context of considering appropriate indications for MDT, detecting metastases at the edge of image resolution should therefore suggest postponing MDT. While three to five lesions are typically used to define OMD, it could be argued that countability throughout the course of metastatic disease, rather than a specific maximum number of lesions, could serve as a better parameter for guiding MDT. Here we argue that the unit of MDT as a treatment option in metastatic cancer might best be defined not as a single procedure at a single point in time, but as a series of treatments that can be delivered in a single or multiple sessions to different lesions over time. Newly emerging lesions that remain amenable to MDT without triggering the start of a new systemic treatment, a change in systemic therapy, or initiation of best supportive care, would thus not constitute a failure of MDT. This would have implications for defining endpoints in clinical trials and registries: Rather than with any disease progression, failure of MDT would only be declared when there is progression to polymetastatic disease, which then precludes further options for MDT.

Background and purpose: Tools for auto-segmentation in radiotherapy are widely available, but guidelines for clinical implementation are missing. The goal was to develop a workflow for performance evaluation of three commercial auto-segmentation tools to select one candidate for clinical implementation. Materials and Methods: One hundred patients with six treatment sites (brain, head-and-neck, thorax, abdomen, and pelvis) were included. Three sets of AI-based contours for organs-at-risk (OAR) generated by three software tools and manually drawn expert contours were blindly rated for contouring accuracy. The dice similarity coefficient (DSC), the Hausdorff distance, and a dose/volume evaluation based on the recalculation of the original treatment plan were assessed. Statistically significant differences were tested using the Kruskal-Wallis test and the post-hoc Dunn Test with Bonferroni correction. Results: The mean DSC scores compared to expert contours for all OARs combined were 0.80 ± 0.10, 0.75 ± 0.10, and 0.74 ± 0.11 for the three software tools. Physicians' rating identified equivalent or superior performance of some AI-based contours in head (eye, lens, optic nerve, brain, chiasm), thorax (e.g., heart and lungs), and pelvis and abdomen (e.g., kidney, femoral head) compared to manual contours. For some OARs, the AI models provided results requiring only minor corrections. Bowel-bag and stomach were not fit for direct use. During the interdisciplinary discussion, the physicians' rating was considered the most relevant. Conclusion: A comprehensive method for evaluation and clinical implementation of commercially available auto-segmentation software was developed. The in-depth analysis yielded clear instructions for clinical use within the radiotherapy department.

Purpose: In image-guided adaptive brachytherapy (IGABT) a quantitative evaluation of the dosimetric changes between fractions due to anatomical variations, can be implemented via rigid registration of images from subsequent fractions based on the applicator as a reference structure. With available treatment planning systems (TPS), this is a manual and time-consuming process. The aim of this retrospective study was to automate this process. A neural network (NN) was trained to predict the applicator structure from MR images. The resulting segmentation was used to automatically register MR-volumes. Material and Methods: DICOM images and plans of 56 patients treated for cervical cancer with high dose-rate (HDR) brachytherapy were used in the study. A 2D and a 3D NN were trained to segment applicator structures on clinical T2-weighted MRI datasets. Different rigid registration algorithms were investigated and compared. To evaluate a fully automatic registration workflow, the NN-predicted applicator segmentations (AS) were used for rigid image registration with the best performing algorithm. The DICE coefficient and mean distance error between dwell positions (MDE) were used to evaluate segmentation and registration performance. Results: The mean DICE coefficient for the predicted AS was 0.70 ± 0.07 and 0.58 ± 0.04 for the 3D NN and 2D NN, respectively. Registration algorithms achieved MDE errors from 8.1 ± 3.7 mm (worst) to 0.7 ± 0.5 mm (best), using ground-truth AS. Using the predicted AS from the 3D NN together with the best registration algorithm, an MDE of 2.7 ± 1.4 mm was achieved. Conclusion: Using a combination of deep learning models and state of the art image registration techniques has been demonstrated to be a promising solution for automatic image registration in IGABT. In combination with auto-contouring of organs at risk, the auto-registration workflow from this study could become part of an online-dosimetric interfraction evaluation workflow in the future.

Purpose: For image translational tasks, the application of deep learning methods showed that Generative Adversarial Network (GAN) architectures outperform the traditional U-Net networks, when using the same training data size. This study investigates whether this performance boost can also be expected for segmentation tasks with small training dataset size. Materials/Methods: Two models were trained on varying training dataset sizes ranging from 1—100 patients: a) U-Net and b) U-Net with patch discriminator (conditional GAN). The performance of both models to segment the male pelvis on CT-data was evaluated (Dice similarity coefficient, Hausdorff) with respect to training data size. Results: No significant differences were observed between the U-Net and cGAN when the models were trained with the same training sizes up to 100 patients. The training dataset size had a significant impact on the models’ performances, with vast improvements when increasing dataset sizes from 1 to 20 patients. Conclusion: When introducing GANs for the segmentation task no significant performance boost was observed in our experiments, even in segmentation models developed on small datasets.

Purpose: To investigate the sensitivity of patient-reported outcome measures (PROMs) to detect treatment-related side effects in patients with breast cancer undergoing external beam photon radiotherapy. Methods: As part of daily clinical care, an in-house developed PROM tool was used to assess side effects in patients during a) whole-breast irradiation (WBI) to 40 Gy, b) WBI with a sequential boost of 10 Gy, and c) partial-breast irradiation (PBI) to 40 Gy. Results: 414 patients participated in this prospective study between October 2020 and January 2022, with 128 patients (31 %) receiving WBI, 241 (58 %) receiving WBI followed by a sequential boost, and 50 patients (12 %) receiving PBI. Significant differences in the reported toxicities (itching, radiation skin reaction, skin darkening, and tenderness and swelling) were reported between the WBI cohorts with and without boost (p

As a result of the energy transition, an increasing number of Decentralized Energy Systems (DES) will be installed in the distribution grid in the future. Accordingly, new methods to systematically integrate the growing DES in distribution power systems must be developed utilizing the constantly evolving Information and Communication Technologies (ICT). This paper proposes the Automated Data Model Integration of DES (ADMID) approach for the integration of DES into the ICT environment of the Distribution System Operator (DSO). The proposed ADMID utilizes the data model structure defined by the standard-series IEC 61850 and has been implemented as a Python package. The presented two Use Cases focus on the Supervisory Control and Data Acquisition (SCADA) on the DSO operational level following a four-stage test procedure, while this approach has enormous potential for advanced DSO applications. The test results obtained during simulation or real-time communication to field devices indicate that the utilization of IEC 61850-compliant data models is eligible for the proposed automation approach, and the implemented framework can be a considerable solution for the system integration in future distribution grids with a high share of DES. As a proof-of-concept study, the proposed ADMID approach requires additional development with a focus on the harmonization with the Common Information Model (CIM), which could significantly improve its functional interoperability and help it reach a higher Technology Readiness Level (TRL).

The fundamental changes in the energy sector, due to the rise of renewable energy resources and the possibilities of the digitalisation process, result in the demand for new methodologies for testing Smart Grid concepts and control strategies. Using the Power Hardware-in-the-Loop (PHIL) methodology is one of the key elements for such evaluations. PHIL and other in-the-loop concepts cannot be considered as plug’n’play and, for a wider adoption, the obstacles have to be reduced. This paper presents the comparison of two different setups for the evaluation of components and systems focused on undisturbed operational conditions. The first setup is a conventional PHIL setup and the second is a simplified setup based on a quasi-dynamic PHIL (QDPHIL) approach which involves fast and continuously steady state load flow calculations. A case study which analyses a simple superimposed voltage control algorithm gives an example for the actual usage of the quasi-dynamic setup. Furthermore, this article also provides a comparison and discussion of the achieved results with the two setups and it concludes with an outlook about further research.