The livestock sector has complex relationships with the three fundamental pillars of sustainability, i.e., environmental, economic, and social. Devising a livestock farming strategy by considering the different sustainability pillars is essential. Although several decision support systems (DSSs) are available for the livestock sector, these DSSs differ in the way they address sustainability. This work emphasizes the importance of a holistic approach to sustainable livestock management rather than only targeting individual sustainability dimensions. We, therefore, propose an initial assessment framework to evaluate the capacity of livestock DSSs in targeting the different sustainability pillars. In line with this, we present a conceptual basis for deriving assessment criteria and indicators. We then use the proposed assessment framework to assess existing openly available livestock DSSs. We observe that the main focus of the existing and openly available livestock-related DSSs is on the indicators from environmental pillars, and only a few of them accommodate economic aspects. No openly available DSS includes social and governance-related points. More importantly, none of these DSSs can handle data streams from Internet of Things (IoT) devices and, hence, they miss on the superiority that advanced modelling techniques can provide. With these observations, we draft an extensive set of guidelines for future livestock-related DSSs to holistically target sustainability.

Agent-based models are often used to explore the potentialconsequences of different assumptions or scenarios and support decision-making in complex systems. One challenge in employing agent-basedmodels for decision-making is identifying the appropriate level of detailand granularity of the models in relation to the decision-relevant ques-tions. On the one hand, more detailed and granular models may providemore accurate and nuanced insights, but they may also be more chal-lenging to interpret and may require more time and resources to run andanalyze. On the other hand, simpler and more aggregated models may beeasier to interpret and may be more efficient to run, but they may alsosacrifice some accuracy and nuance in the process. In this paper, we ex-plore the trade-offs between detailed and aggregated models and discussthe factors that influence the appropriate level of detail and granularity.

The rapid growth in industrialization and the increasing demand for energy have brought about a critical need for energy efficiency in various industries. Adopting intelligent manufacturing techniques is imperative to optimize energy consumption and reduce environmental impacts caused by traditional manufacturing processes. Enhancing energy efficiency in manufacturing involves real-time monitoring, improved control mechanisms, modeling tools, and energy-efficient equipment. Two key fronts can be addressed to enhance energy efficiency in the industry: utilizing renewable energy sources for production and reducing energy consumption in manufacturing systems. Digital twins, serving as virtual replicas of assets or processes, offer a promising solution by enabling efficient monitoring and optimization in both areas. This comprehensive approach ensures enhanced energy efficiency in industrial settings. Digital twins should enable real-time monitoring, data analysis, and simulation of manufacturing processes, providing valuable insights into energy consumption patterns and identifying areas for improvement. By integrating the principles of Industry 4.0 and Internet of Things (IoT) technologies, digital twins facilitate the implementation of advanced energy management strategies and enable proactive decision-making. This research explores the importance of energy efficiency in the manufacturing sector and highlights the potential benefits of employing digital twins in achieving energy optimization and also highlights the primary challenges associated with employing digital twins for energy-efficient manufacturing. As a result, we propose a conceptual framework to address the challenges and complexities associated with implementing digital twins for energy efficiency in manufacturing. The framework includes the definition of objectives and metrics, data collection and integration from various sources, data validation, knowledge extraction, and model development and validation. Our framework utilizes well-established Key Performance Indicators (KPIs) for energy-related performance evaluation in manufacturing, offers visualization and simulation capabilities, and enables real-time feedback and control for optimizing energy usage and improving overall efficiency. Lastly, performance evaluation and reporting in digital twins for energy efficiency is proposed as a process that evaluates and measures the performance of digital twins in relation to energy efficiency, and then reports to stakeholders, providing valuable insights into energy efficiency performance and guiding decision-making for further enhancements.

In today's industrial landscape, manufacturing systems face challenges that have significant implications for productivity, efficiency, and overall performance. The growing complexity of these systems and the need for optimization, efficient resource allocation, and adaptability demand innovative approaches. One solution that has gained prominence are digital twins (DTs), which are virtual replicas of physical manufacturing systems that can address the challenges faced by modern manufacturing systems. DTs enable methods like predictive maintenance and simulation-based optimization. Consequently, companies have a strong motivation to develop DTs for their manufacturing systems. Our research focuses on an especially challenging case, i.e., humancentric manufacturing systems. These involve the active human participation, often driven by intrinsic motivation rather than strictly adhering to predefined protocols. This poses additional challenges in automating the creation of their DTs. On one hand, human behaviors introduce specific uncertainties, which must be appropriately considered in the model; not only are production cycles never identical, but factors like motivation, well-being, and energy levels constantly fluctuate. On the other hand, the processes of collecting data become more complex as human workers require additional hardware, such as wearables, to effectively gather relevant data. Consequently, there currently may be a significant imbalance in the data, with sparse representation for the human-related steps and abundant data available for the machine-related ones. In addition, the collection of worker-related data may lead to privacy concerns that will need to be addressed as well. Due to the aforementioned challenges, most DTs for humancentric manufacturing systems are currently created manually, which is a labor-intensive and time-consuming process. Moreover, the need to adapt production based on economic factors and derived goals leads to continuously adjusting the underlying models, significantly increasing maintenance costs. However, many companies possess large amounts of machine-related manufacturing data that can be leveraged to automate model extraction processes. Process mining is one such technique that automatically extracts underlying process flows in manufacturing systems from their event logs. Extracted process flows form the basis for the machine-related part of the DTs. To complete DTs, the human-related processes need to be integrated. This integration starts by defining the goals of the human-related portion of DTs and subsequently identifying or adjusting the relevant performance metrics. Our goal is to develop a general framework and methodology that links these performance metrics to data streams to enable data-driven DTs for humancentric manufacturing systems.

Predicting remaining cycle times of products in manufacturing systems is critical to ensure on-time deliveries to customers, schedule resources and actions for expected order completions, and address excessive production stops proactively rather than retroactively. Recent advances in Predictive Process Monitoring (PPM), a sub-discipline of Process Mining, enable the use of machine learning to predict remaining cycle times based on event data. We apply PPM to the automated manufacturing domain and demonstrate the approach using a case study from a water meter manufacturer. For prediction of remaining cycle times, PPM relies on regression methods, such as Decision Trees, Random Forests, and Gradient Boosting Machines based on event data. We compare the prediction accuracy of these methods and show that PPM can deliver relevant insights for production lines without imposing extensive data requirements.