The continuously increasing complexity of modern and sustainable power and energy systems leads to a wide range of solutions developed by industry and academia. To manage such complex system-of-systems, proper engineering and validation approaches, methods, concepts, and corresponding tools are necessary. The Smart Grid Architecture Model (SGAM), an approach that has been developed during the last couple of years, provides a very good and structured basis for the design, development, and validation of new solutions and technologies. This review therefore provides a comprehensive overview of the state-of-the-art and related work for the theory, distribution, and use of the aforementioned architectural concept. The article itself provides an overview of the overall method and introduces the theoretical fundamentals behind this approach. Its usage is demonstrated in several European and national research and development projects. Finally, an outlook about future trends, potential adaptations, and extensions is provided as well.

In these days, when complex, IT-controlled systems have found their way into many areas, models and the data on which they are based are playing an increasingly important role. Due to the constantly growing possibilities of collecting data through sensor technology, extensive data sets are created that need to be mastered. In concrete terms, this means extracting the information required for a specific problem from the data in a high quality. For example, in the field of condition monitoring, this includes relevant system states. Especially in the application field of machine learning, the quality of the data is of significant importance. Here, different methods already exist to reduce the size of data sets without reducing the information value. In this paper, the multidimensional binned reduction (MdBR) method is presented as an approach that has a much lower complexity in comparison on the one hand and deals with regression, instead of classification as most other approaches do, on the other. The approach merges discretization approaches with non-parametric numerosity reduction via histograms. MdBR has linear complexity and can be facilitated to reduce large multivariate data sets to smaller subsets, which could be used for model training. The evaluation, based on a dataset from the photovoltaic sector with approximately 92 million samples, aims to train a multilayer perceptron (MLP) model to estimate the output power of the system. The results show that using the approach, the number of samples for training could be reduced by more than $99\%$, while also increasing the model’s performance. It works best with large data sets of low-dimensional data. Although periodic data often include the most redundant samples and thus provide the best reduction capabilities, the presented approach can only handle time-invariant data and not sequences of samples, as often done in time series.

This Editorial provides an introduction to the Special Issue “Methods and Concepts for Designing and Validating Smart Grid Systems”. Furthermore, it also provides an overview of the corresponding papers that where recently published in MDPI’s Energies journal. The Special Issue took place in 2018 and accepted a total of 19 papers from 19 different countries.

Data imbalance persists as a pervasive challenge in regression tasks, introducing bias in model performance and undermining predictive reliability. This is particularly detrimental in applications aimed at predicting rare events that fall outside the domain of the bulk of the training data. In this study, we review the current state-of-the-art regarding sampling-based methods and cost-sensitive learning. Additionally, we propose novel approaches to mitigate model bias. To better asses the importance of data, we introduce the density-distance and density-ratio relevance functions, which effectively integrate empirical frequency of data with domain-specific preferences, offering enhanced interpretability for end-users. Furthermore, we present advanced mitigation techniques (cSMOGN and crbSMOGN), which build upon and improve existing sampling methods. In a comprehensive quantitative evaluation, we benchmark state-of-the-art methods on 10 synthetic and 42 real-world datasets, using neural networks, XGBoosting trees and Random Forest models. Our analysis reveals that while most strategies improve performance on rare samples, they often degrade it on frequent ones. We demonstrate that constructing an ensemble of models -- one trained with imbalance mitigation and another without -- can significantly reduce these negative effects. The key findings underscore the superior performance of our novel crbSMOGN sampling technique with the density-ratio relevance function for neural networks, outperforming state-of-the-art methods.

Evaluating new technological developments for energy systems is becoming more and more complex. The overall application environment is a continuously growing and interconnected cyber-physical system so that analytical assessment is practically impossible to realize. Consequently, new solutions must be evaluated in simulation studies. Due to the interdisciplinarity of the simulation scenarios, various heterogeneous tools must be connected. This approach is known as co-simulation. During the last years, different approaches have been developed or adapted for applications in energy systems. In this paper, two co-simulation approaches are compared that follow generic, versatile concepts. The tool mosaik, which has been explicitly developed for the purpose of co-simulation in complex energy systems, is compared to the High Level Architecture (HLA), which possesses a domain-independent scope but is often employed in the energy domain. The comparison is twofold, considering the tools' conceptual architectures as well as results from the simulation of representative test cases. It suggests that mosaik may be the better choice for entry-level, prototypical co-simulation while HLA is more suited for complex and extensive studies.