A Digital Twin (DT) of a production plant is a digital replica of the plant's physical assets which contains the structure and the dynamics of how the devices and process operate. Simulation-based DTs (SBDTs) are those based on online first-principles simulation models. In these systems, model parameter estimation techniques keep an online plant simulator in the same state as the targeted device or process. As a result, non-measured information of the current state of the plant can be obtained from the model. SBDTs can be used for a number of important applications and they have various advantages compared to DTs based on data-driven models. However, wider industrial adoption of SBDTs is hindered by laborious development of their underlying first-principles simulation model as well as by a lack of integrated lifecycle-wide implementation methods and simulation architectures. This paper focuses on applying previously presented methods for reducing implementation effort of SBDTs. Firstly, laborious simulation model development is tackled by applying an automatic model generation method. Secondly, an integrated implementation methodology of a lifecycle-wide online simulation architecture is followed for developing the SBDT. A SBDT of a laboratory-scale process is implemented to demonstrate the proposed method. The results show a higher level of fidelity compared to previous publications.

In the Software Development Life Cycle (SDLC), Development and Operations (DevOps) has been proven to deliver reliable, scalable software within a shorter time. Due to the explosion of Machine Learning (ML) applications, the term Machine Learning Operations (MLOps) has gained significant interest among ML practitioners. This paper explains the DevOps and MLOps processes relevant to the implementation of MLOps. The contribution of this paper towards the MLOps framework is threefold: First, we review the state of the art in MLOps by analyzing the related work in MLOps. Second, we present an overview of the leading DevOps principles relevant to MLOps. Third, we derive an MLOps framework from the MLOps theory and apply it to a time-series forecasting application in the hourly day-ahead electricity market. The paper concludes with how MLOps could be generalized and applied to two more use cases with minor changes.

Research, the universal pursuit of new knowledge, is embarking on a fresh journey into artificial intelligence (AI). Nature reports that AI arose nine places to the fourth-most popular search term and that search terms machine learning and deep learning appeared in the top 20 for the first time since 2018. It is pertinent for industrial informatics to embrace this renewed surge of interest in AI with a clear direction and purpose that engages scholars, practitioners, and professionals alike.

Reinforcement learning has emerged as a potentially disruptive technology for control and optimization of HVAC systems. A reinforcement learning agent takes actions, which can be direct HVAC actuator commands or setpoints for control loops in building automation systems. The actions are taken to optimize one or more targets, such as indoor air quality, energy consumption and energy cost. The agent receives feedback from the HVAC systems to quantify how well these targets have been achieved. The feedback is captured by a reward function designed by the developer of the reinforcement learning agent. A few reviews have focused on the reward aspect of reinforcement learning applications for HVAC. However, there is a lack of reviews that assess how the actions of the reinforcement learning agent have been formulated, and how this impacts the possibilities to achieve various optimization targets in single zone or multi-zone buildings. The aim of this review is to identify the action formulations in the literature and to assess how the choice of formulation impacts the level of abstraction at which the HVAC systems are considered. Our methodology involves a search string in the Web of Science database and a list of selection criteria applied to each article in the search results. For each selected article, a three-tier categorization of the selected articles has been performed. Firstly, the applicability of the approach to buildings with one or more zones is considered. Secondly, the articles are categorized by the type of action taken by the agent, such as a binary, discrete or continuous action. Thirdly, the articles are categorized by the aspects of the indoor environment being controlled, namely temperature, humidity or air quality. The main result of the review is this three-tier categorization that reveals the community’s emphasis on specific HVAC applications, as well as the readiness to interface the reinforcement learning solutions to HVAC systems. The article concludes with a discussion of trends in the field as well as challenges that require further research.