We explore a Digital Twin-Based Approach for Smart Manufacturing to improve Sustainability, Efficiency, and Cost-Effectiveness for a steel production plant. Our system is based on a micro-service edge-compute platform that ingests real-time sensor data from the process into a digital twin over a converged network infrastructure. We implement agile machine learning-based control loops in the digital twin to optimize induction furnace heating, enhance operational quality, and reduce process waste. Key to our approach is a Deep Reinforcement learning-based agent used in our machine learning operation (MLOps) driven system to autonomously correlate the system state with its digital twin to identify correction actions that aim to optimize power settings for the plant. We present the theoretical basis, architectural details, and practical implications of our approach to reduce manufacturing waste and increase production quality. We design the system for flexibility so that our scalable event-driven architecture can be adapted to various industrial applications. With this research, we propose a pivotal step towards the transformation of traditional processes into intelligent systems, aligning with sustainability goals and emphasizing the role of MLOps in shaping the future of data-driven manufacturing.

Abstract Heat pumps (HPs) have emerged as a cost-effective and clean technology for sustainable energy systems, but their efficiency in producing hot water remains restricted by conventional threshold-based control methods. Although machine learning (ML) has been successfully implemented for various HP applications, optimization of household hot water demand forecasting remains understudied. This paper addresses this problem by introducing a novel approach that combines predictive ML with anomaly detection to create adaptive hot water production strategies based on household-specific consumption patterns. Our key contributions include: (1) a composite approach combining ML and isolation forest (iForest) to forecast household demand for hot water and steer responsive HP operations; (2) multi-step feature selection with advanced time series analysis to capture complex usage patterns; (3) application and tuning of three ML models: light gradient boosting machine (LightGBM), long short-term memory (LSTM), and bidirectional LSTM with the self-attention mechanism on data from different types of real HP installations; and (4) experimental validation on six real household installations. Our experiments show that the best-performing model LightGBM achieves superior performance, with RMSE improvements of up to 9.37% compared to LSTM variants with $$R^2$$ R 2 values between 0.748 $$-$$ - 0.983. For anomaly detection, our iForest implementation achieved an F1-score of 0.87 with a false alarm rate of only 5.2%, demonstrating strong generalization capabilities across different household types and consumption patterns, making it suitable for real-world HP deployments.

The rapidly changing landscapes of modern optimization problems require algorithms that can be adapted in real-time. This paper introduces an Adaptive Metaheuristic Framework (AMF) designed for dynamic environments. It is capable of intelligently adapting to changes in the problem parameters. The AMF combines a dynamic representation of problems, a real-time sensing system, and adaptive techniques to navigate continuously changing optimization environments. Through a simulated dynamic optimization problem, the AMF's capability is demonstrated to detect environmental changes and proactively adjust its search strategy. This framework utilizes a differential evolution algorithm that is improved with an adaptation module that adjusts solutions in response to detected changes. The capability of the AMF to adjust is tested through a series of iterations, demonstrating its resilience and robustness in sustaining solution quality despite the problem's development. The effectiveness of AMF is demonstrated through a series of simulations on a dynamic optimization problem. Robustness and agility characterize the algorithm's performance, as evidenced by the presented fitness evolution and solution path visualizations. The findings show that AMF is a practical solution to dynamic optimization and a major step forward in the creation of algorithms that can handle the unpredictability of real-world problems.

Augmented Reality (AR) and Virtual Reality (VR) systems involve computationally intensive image processing algorithms that can burden end-devices with limited resources, leading to poor performance in providing low latency services. Edge-to-cloud computing overcomes the limitations of end-devices by offloading their computations to nearby edge devices or remote cloud servers. Although this proves to be sufficient for many applications, optimal placement of latency sensitive AR/VR services in edge-to-cloud infrastructures (to provide desirable service response times and reliability) remain a formidable challenging. To address this challenge, this paper develops a Multi-Objective Genetic Algorithm (MOGA) to optimize the placement of AR/VR-based services in multi-tier edge-to-cloud environments. The primary objective of the proposed MOGA is to minimize the response time of all running services, while maximizing the reliability of the underlying system from both software and hardware perspectives. To evaluate its performance, we mathematically modeled all components and developed a tailor-made simulator to assess its effectiveness on various scales. MOGA was compared with several heuristics to prove that intuitive solutions, which are usually assumed sufficient, are not efficient enough for the stated problem. The experimental results indicated that MOGA can significantly reduce the response time of deployed services by an average of 67% on different scales, compared to other heuristic methods. MOGA also ensures reliability of the 97% infrastructure (hardware) and 95% services (software).

Within data-driven artificial intelligence (AI) systems for industrial applications, ensuring the reliability of theincoming data streams is an integral part of trustworthy decision-making. An approach to assess data validityis data quality scoring, which assigns a score to each data point or stream based on various quality dimensions.However, certain dimensions exhibit dynamic qualities, which require adaptation on the basis of the system’scurrent conditions. Existing methods often overlook this aspect, making them inefficient in dynamic productionenvironments. In this paper, we introduce the Adaptive Data Quality Scoring Operations Framework, a novelframework developed to address the challenges posed by dynamic quality dimensions in industrial data streams.The framework introduces an innovative approach by integrating a dynamic change detector mechanism thatactively monitors and adapts to changes in data quality, ensuring the relevance of quality scores. We evaluatethe proposed framework performance in a real-world industrial use case. The experimental results reveal highpredictive performance and efficient processing time, highlighting its effectiveness in practical quality-drivenAI applications.

Data quality assessment has become a prominent component in the successful execution of complex data-driven artificial intelligence (AI) software systems. In practice, real-world applications generate huge volumes of data at speeds. These data streams require analysis and preprocessing before being permanently stored or used in a learning task. Therefore, significant attention has been paid to the systematic management and construction of high-quality datasets. Nevertheless, managing voluminous and high-velocity data streams is usually performed manually (i.e. offline), making it an impractical strategy in production environments. To address this challenge, DataOps has emerged to achieve life-cycle automation of data processes using DevOps principles. However, determining the data quality based on a fitness scale constitutes a complex task within the framework of DataOps. This paper presents a novel Data Quality Scoring Operations (DQSOps) framework that yields a quality score for production data in DataOps workflows. The framework incorporates two scoring approaches, an ML prediction-based approach that predicts the data quality score and a standard-based approach that periodically produces the ground-truth scores based on assessing several data quality dimensions. We deploy the DQSOps framework in a real-world industrial use case. The results show that DQSOps achieves significant computational speedup rates compared to the conventional approach of data quality scoring while maintaining high prediction performance.

Load forecasting is a crucial topic in energy management systems (EMS) due to its vital role in optimizing energy scheduling and enabling more flexible and intelligent power grid systems. As a result, these systems allow power utility companies to respond promptly to demands in the electricity market. Deep learning (DL) models have been commonly employed in load forecasting problems supported by adaptation mechanisms to cope with the changing pattern of consumption by customers, known as concept drift. A drift magnitude threshold should be defined to design change detection methods to identify drifts. While the drift magnitude in load forecasting problems can vary significantly over time, existing literature often assumes a fixed drift magnitude threshold, which should be dynamically adjusted rather than fixed during system evolution. To address this gap, in this paper, we propose a dynamic drift-adaptive Long Short-Term Memory (DA-LSTM) framework that can improve the performance of load forecasting models without requiring a drift threshold setting. We integrate several strategies into the framework based on active and passive adaptation approaches. To evaluate DA-LSTM in real-life settings, we thoroughly analyze the proposed framework and deploy it in a real-world problem through a cloud-based environment. Efficiency is evaluated in terms of the prediction performance of each approach and computational cost. The experiments show performance improvements on multiple evaluation metrics achieved by our framework compared to baseline methods from the literature. Finally, we present a trade-off analysis between prediction performance and computational costs.

Abstract Most machine learning methods assume that the input data distribution is the same in the training and testing phases. However, in practice, this stationarity is usually not met and the distribution of inputs differs, leading to unexpected performance of the learned model in deployment. The issue in which the training and test data inputs follow different probability distributions while the input–output relationship remains unchanged is referred to as covariate shift. In this paper, the performance of conventional machine learning models was experimentally evaluated in the presence of covariate shift. Furthermore, a region-based evaluation was performed by decomposing the domain of probability density function of the input data to assess the classifier’s performance per domain region. Distributional changes were simulated in a two-dimensional classification problem. Subsequently, a higher four-dimensional experiments were conducted. Based on the experimental analysis, the Random Forests algorithm is the most robust classifier in the two-dimensional case, showing the lowest degradation rate for accuracy and F1-score metrics, with a range between 0.1% and 2.08%. Moreover, the results reveal that in higher-dimensional experiments, the performance of the models is predominantly influenced by the complexity of the classification function, leading to degradation rates exceeding 25% in most cases. It is also concluded that the models exhibit high bias toward the region with high density in the input space domain of the training samples.

Most industrial processes in real-world manufacturing applications are characterized by the scalability property, which requires an automated strategy to self-adapt machine learning (ML) software systems to the new conditions. In this paper, we investigate an Electroslag Remelting (ESR) use case process from the Uddeholms AB steel company. The use case involves predicting the minimum pressure value for a vacuum pumping event. Taking into account the long time required to collect new records and efficiently integrate the new machines with the built ML software system. Additionally, to accommodate the changes and satisfy the non-functional requirement of the software system, namely adaptability, we propose an automated and adaptive approach based on a drift handling technique called importance weighting. The aim is to address the problem of adding a new furnace to production and enable the adaptability attribute of the ML software. The overall results demonstrate the improvements in ML software performance achieved by implementing the proposed approach over the classical non-adaptive approach.

There is often a scarcity of training data for machine learning (ML) classification and regression models in industrial production, especially for time-consuming or sparsely run manufacturing processes. Traditionally, a majority of the limited ground-truth data is used for training, while a handful of samples are left for testing. In that case, the number of test samples is inadequate to properly evaluate the robustness of the ML models under test (i.e., the system under test) for classification and regression. Furthermore, the output of these ML models may be inaccurate or even fail if the input data differ from the expected. This is the case for ML models used in the Electroslag Remelting (ESR) process in the refined steel industry to predict the pressure in a vacuum chamber. A vacuum pumping event that occurs once a workday generates a few hundred samples in a year of pumping for training and testing. In the absence of adequate training and test samples, this paper first presents a method to generate a fresh set of augmented samples based on vacuum pumping principles. Based on the generated augmented samples, three test scenarios and one test oracle are presented to assess the robustness of an ML model used for production on an industrial scale. Experiments are conducted with real industrial production data obtained from Uddeholms AB steel company. The evaluations indicate that Ensemble and Neural Network are the most robust when trained on augmented data using the proposed testing strategy. The evaluation also demonstrates the proposed method's effectiveness in checking and improving ML algorithms' robustness in such situations. The work improves software testing's state-of-the-art robustness testing in similar settings. Finally, the paper presents an MLOps implementation of the proposed approach for real-time ML model prediction and action on the edge node and automated continuous delivery of ML software from the cloud.

Finite State Machine is a popular modeling notation for various systems, especially software and electronic. Test paths (TPs) can be automatically generated from the system model to test such systems using a suitable algorithm. This paper presents a strategy that generates TPs and allows to start and end TPs only in defined states of the finite state machine. The strategy also simultaneously supports generating TPs only of length in a given range. For this purpose, alternative system models, test coverage criteria, and a set of algorithms are developed. The strategy is compared with the best alternative based on the reduction of the test set generated by the established N-switch coverage approach on a mix of 171 industrial and artificially generated problem instances. The proposed strategy outperforms the compared variant in a smaller number of TP steps. The extent varies with the used test coverage criterion and preferred TP length range from none to two and half fold difference. Moreover, the proposed technique detected up to 30% more simple artificial defects inserted into experimental SUT models per one test step than the compared alternative technique. The proposed strategy is well applicable in situations where a possible TP starts and ends in a state machine needs to be reflected and, concurrently, the length of the TPs has to be in a defined range.

The dynamicity of real-world systems poses a significant challenge to deployed predictive machine learning (ML) models. Changes in the system on which the ML model has been trained may lead to performance degradation during the system’s life cycle. Recent advances that study non-stationary environments have mainly focused on identifying and addressing such changes caused by a phenomenon called concept drift. Different terms have been used in the literature to refer to the same type of concept drift and the same term for various types. This lack of unified terminology is set out to create confusion on distinguishing between different concept drift variants. In this paper, we start by grouping concept drift types by their mathematical definitions and survey the different terms used in the literature to build a consolidated taxonomy of the field. We also review and classify performance-based concept drift detection methods proposed in the last decade. These methods utilize the predictive model’s performance degradation to signal substantial changes in the systems. The classification is outlined in a hierarchical diagram to provide an orderly navigation between the methods. We present a comprehensive analysis of the main attributes and strategies for tracking and evaluating the model’s performance in the predictive system. The paper concludes by discussing open research challenges and possible research directions.

Software module clustering is an unsupervised learning method used to cluster software entities (e.g., classes, modules, or files) with similar features. The obtained clusters may be used to study, analyze, and understand the software entities’ structure and behavior. Implementing software module clustering with optimal results is challenging. Accordingly, researchers have addressed many aspects of software module clustering in the past decade. Thus, it is essential to present the research evidence that has been published in this area. In this study, 143 research papers from well-known literature databases that examined software module clustering were reviewed to extract useful data. The obtained data were then used to answer several research questions regarding state-of-the-art clustering approaches, applications of clustering in software engineering, clustering processes, clustering algorithms, and evaluation methods. Several research gaps and challenges in software module clustering are discussed in this paper to provide a useful reference for researchers in this field.

With the rapid growth of the contemporary Internet of Things (IoT) market, the established systems raise a number of concerns regarding the reliability and the potential presence of critical integration defects. In this paper, we present a PatrIoT framework that aims to provide flexible support to construct an effective IoT system testbed to implement automated interoperability and integration testing. The framework allows scaling from a pure physical testbed to a simulated environment using a number of predefined modules and elements to simulate an IoT device or part of the tested infrastructure. PatrIoT also contains a set of reference example testbeds and several sets of example automated tests for a smart street use case.

A natural method to evaluate the effectiveness of a testing technique is to measure the defect detection rate when applying the created test cases. Here, real or artificial software defects can be injected into the source code of software. For a more extensive evaluation, injection of artificial defects is usually needed and can be performed via mutation testing using code mutation operators. However, to simulate complex defects arising from a misunderstanding of design specifications, mutation testing might reach its limit in some cases. In this paper, we present an open-source benchmark testbed application that employs a complement method of artificial defect injection. The application is compiled after artificial defects are injected into its source code from predefined building blocks. The majority of the functions and user interface elements are covered by creating front-end-based automated test cases that can be used in experiments.

To ensure the quality of current highly configurable software systems, intensive testing is needed to test all the configuration combinations and detect all the possible faults. This task becomes more challenging for most modern software systems when constraints are given for the configurations. Here, intensive testing is almost impossible, especially considering the additional computation required to resolve the constraints during the test generation process. In addition, this testing process is exhaustive and time-consuming. Combinatorial interaction strategies can systematically reduce the number of test cases to construct a minimal test suite without affecting the effectiveness of the tests. This paper presents a new efficient search-based strategy to generate constrained interaction test suites to cover all possible combinations. The paper also shows a new application of constrained interaction testing in software fault searches. The proposed strategy initially generates the set of all possible [Formula: see text]-[Formula: see text] combinations; then, it filters out the set by removing the forbidden [Formula: see text]-[Formula: see text] using the Base Forbidden Tuple (BFT) approach. The strategy also utilizes a mixed neighborhood tabu search (TS) to construct optimal or near-optimal constrained test suites. The efficiency of the proposed method is evaluated through a comparison against two well-known state-of-the-art tools. The evaluation consists of three sets of experiments for 35 standard benchmarks. Additionally, the effectiveness and quality of the results are assessed using a real-world case study. Experimental results show that the proposed strategy outperforms one of the competitive strategies, ACTS, for approximately 83% of the benchmarks and achieves similar results to CASA for 65% of the benchmarks when the interaction strength is 2. For an interaction strength of 3, the proposed method outperforms other competitive strategies for approximately 60% and 42% of the benchmarks. The proposed strategy can also generate constrained interaction test suites for an interaction strength of 4, which is not possible for many strategies. The real-world case study shows that the generated test suites can effectively detect injected faults using mutation testing.

Abstract Hyper-heuristic is a new methodology for the adaptive hybridization of meta-heuristic algorithms to derive a general algorithm for solving optimization problems. This work focuses on the selection type of hyper-heuristic, called the exponential Monte Carlo with counter (EMCQ). Current implementations rely on the memory-less selection that can be counterproductive as the selected search operator may not (historically) be the best performing operator for the current search instance. Addressing this issue, we propose to integrate the memory into EMCQ for combinatorial t-wise test suite generation using reinforcement learning based on the Q-learning mechanism, called Q-EMCQ. The limited application of combinatorial test generation on industrial programs can impact the use of such techniques as Q-EMCQ. Thus, there is a need to evaluate this kind of approach against relevant industrial software, with a purpose to show the degree of interaction required to cover the code as well as finding faults. We applied Q-EMCQ on 37 real-world industrial programs written in Function Block Diagram (FBD) language, which is used for developing a train control management system at Bombardier Transportation Sweden AB. The results show that Q-EMCQ is an efficient technique for test case generation. Addition- ally, unlike the t-wise test suite generation, which deals with the minimization problem, we have also subjected Q-EMCQ to a maximization problem involving the general module clustering to demonstrate the effectiveness of our approach. The results show the Q-EMCQ is also capable of outperforming the original EMCQ as well as several recent meta/hyper-heuristic including modified choice function, Tabu high-level hyper-heuristic, teaching learning-based optimization, sine cosine algorithm, and symbiotic optimization search in clustering quality within comparable execution time.

Combinatorial interaction testing (CIT) is a well-known technique, but the industrial experience is needed to determine its effectiveness in different application domains. We present a case study introducing a unified framework for generating, executing and verifying CIT test suites, based on the open-source Avocado test framework. In addition, we present a new industrial case study to demonstrate the effectiveness of the framework. This evaluation showed that the new framework can generate, execute, and verify effective combinatorial interaction test suites for detecting configuration failures (invalid configurations) in a virtualization system.

Combinatorial interaction testing (CIT) is a useful testing technique to address the interaction of input parameters in software systems. CIT has been used as a systematic technique to sample the enormous test possibilities. Most of the research activities focused on the generation of CIT test suites as a computationally complex problem. Less effort has been paid for the application of CIT. To apply CIT, practitioners must identify the input parameters for the Software‐under‐test (SUT), feed these parameters to the CIT test generation tool, and then run those tests on the application with some pass and fail criteria for verification. Using this approach, CIT is used as a black‐box testing technique without knowing the effect of the internal code. Although useful, practically, not all the parameters having the same impact on the SUT. This paper introduces a different approach to use the CIT as a gray‐box testing technique by considering the internal code structure of the SUT to know the impact of each input parameter and thus use this impact in the test generation stage. The case studies results showed that this approach would help to detect new faults as compared to the equal impact parameter approach.

Testing processes and workflows in information and Internet of Things systems is a major part of the typical software testing effort. Consistent and efficient path-based test cases are desired to support these tests. Because certain parts of software system workflows have a higher business priority than others, this fact has to be involved in the generation of test cases. In this paper, we propose a Prioritized Process Test (PPT), which is a model-based test case generation algorithm that represents an alternative to currently established algorithms that use directed graphs and test requirements to model the system under test. The PPT accepts a directed multigraph as a model to express priorities, and edge weights are used instead of test requirements. To determine the test-coverage level of test cases, a test-depth-level concept is used. We compared the presented PPT with five alternatives (i.e. the Process Cycle Test (PCT), a naive reduction of test set created by the PCT, Brute Force algorithm, Set-covering-Based Solution and Matching-based Prefix Graph Solution) for edge coverage and edge-pair coverage. To assess the optimality of the path-based test cases produced by these strategies, we used 14 metrics based on the properties of these test cases and 59 models that were created for three real-world systems. For all edge coverage, the PPT produced more optimal test cases than the alternatives in terms of the majority of the metrics. For edge-pair coverage, the PPT strategy yielded similar results to those of the alternatives. Thus, the PPT strategy is an applicable alternative as it reflects both the required test coverage level and the business priority in parallel.

For a considerable number of software projects, the creation of effective test cases is hindered by design documentation that is either lacking, incomplete, or obsolete. The exploratory testing approach can serve as a sound method in such situations. However, the efficiency of this testing approach strongly depends on the method, the documentation of explored parts of a system, the organization and distribution of work among individual testers on a team, and the minimization of potential (very probable) duplicities in performed tests. In this paper, we present a framework for replacing and automating a portion of these tasks. A screen-flow-based model of the tested system is incrementally reconstructed during the exploratory testing process by tracking testers' activities. With additional metadata, the model serves for an automated navigation process for a tester. Compared with the exploratory testing approach, which is manually performed in two case studies, the proposed framework allows the testers to explore a greater extent of the tested system and enables greater detection of the defects present in the system. The results show that the time efficiency of the testing process improved with the framework support. This efficiency can be increased by team-based navigational strategies that are implemented within the proposed framework, which is documented by another case study presented in this paper.

As sensor‐related technologies have been developed, smartphones obtain more information from internal and external sensors. This interaction accelerates the development of applications in the Internet of Things environment. Due to many attributes that may vary the quality of the IoT system, sensor manufacturers provide their own data format and application even if there is a well‐defined standard, such as ISO/IEEE 11073 for personal health devices. In this paper, we propose a client‐server‐based sensor adaptation layer for an Android platform to improve interoperability among nonstandard sensors. Interoperability is an important quality aspect for the IoT that may have a strong impact on the system especially when the sensors are coming from different sources. Here, the server compares profiles that have clues to identify the sensor device with a data packet stream based on a modified Boyer‐Moore‐Horspool algorithm. Our matching model considers features of the sensor data packet. To verify the operability, we have implemented a prototype of this proposed system. The evaluation results show that the start and end pattern of the data packet are more efficient when the length of the data packet is longer.