Organizations feel an urgency to develop and implement applications based on foundation models: AI-models that have been trained on large-scale general data and can be finetuned to domain-specific tasks. In this process organizations face many questions, regarding model training and deployment, but also concerning added business value, implementation risks and governance. They express a need for guidance to answer these questions in a suitable and responsible way. We intend to offer such guidance by the question matrix presented in this paper. The question matrix is adjusted from the model card, to match well with development of AIapplications rather than AI-models. First pilots with the question matrix revealed that it elicited discussions among developers and helped developers explicate their choices and intentions during development.
MULTIFILE
The built environment requires energy-flexible buildings to reduce energy peak loads and to maximize the use of (decentralized) renewable energy sources. The challenge is to arrive at smart control strategies that respond to the increasing variations in both the energy demand as well as the variable energy supply. This enables grid integration in existing energy networks with limited capacity and maximises use of decentralized sustainable generation. Buildings can play a key role in the optimization of the grid capacity by applying demand-side management control. To adjust the grid energy demand profile of a building without compromising the user requirements, the building should acquire some energy flexibility capacity. The main ambition of the Brains for Buildings Work Package 2 is to develop smart control strategies that use the operational flexibility of non-residential buildings to minimize energy costs, reduce emissions and avoid spikes in power network load, without compromising comfort levels. To realise this ambition the following key components will be developed within the B4B WP2: (A) Development of open-source HVAC and electric services models, (B) development of energy demand prediction models and (C) development of flexibility management control models. This report describes the developed first two key components, (A) and (B). This report presents different prediction models covering various building components. The models are from three different types: white box models, grey-box models, and black-box models. Each model developed is presented in a different chapter. The chapters start with the goal of the prediction model, followed by the description of the model and the results obtained when applied to a case study. The models developed are two approaches based on white box models (1) White box models based on Modelica libraries for energy prediction of a building and its components and (2) Hybrid predictive digital twin based on white box building models to predict the dynamic energy response of the building and its components. (3) Using CO₂ monitoring data to derive either ventilation flow rate or occupancy. (4) Prediction of the heating demand of a building. (5) Feedforward neural network model to predict the building energy usage and its uncertainty. (6) Prediction of PV solar production. The first model aims to predict the energy use and energy production pattern of different building configurations with open-source software, OpenModelica, and open-source libraries, IBPSA libraries. The white-box model simulation results are used to produce design and control advice for increasing the building energy flexibility. The use of the libraries for making a model has first been tested in a simple residential unit, and now is being tested in a non-residential unit, the Haagse Hogeschool building. The lessons learned show that it is possible to model a building by making use of a combination of libraries, however the development of the model is very time consuming. The test also highlighted the need for defining standard scenarios to test the energy flexibility and the need for a practical visualization if the simulation results are to be used to give advice about potential increase of the energy flexibility. The goal of the hybrid model, which is based on a white based model for the building and systems and a data driven model for user behaviour, is to predict the energy demand and energy supply of a building. The model's application focuses on the use case of the TNO building at Stieltjesweg in Delft during a summer period, with a specific emphasis on cooling demand. Preliminary analysis shows that the monitoring results of the building behaviour is in line with the simulation results. Currently, development is in progress to improve the model predictions by including the solar shading from surrounding buildings, models of automatic shading devices, and model calibration including the energy use of the chiller. The goal of the third model is to derive recent and current ventilation flow rate over time based on monitoring data on CO₂ concentration and occupancy, as well as deriving recent and current occupancy over time, based on monitoring data on CO₂ concentration and ventilation flow rate. The grey-box model used is based on the GEKKO python tool. The model was tested with the data of 6 Windesheim University of Applied Sciences office rooms. The model had low precision deriving the ventilation flow rate, especially at low CO2 concentration rates. The model had a good precision deriving occupancy from CO₂ concentration and ventilation flow rate. Further research is needed to determine if these findings apply in different situations, such as meeting spaces and classrooms. The goal of the fourth chapter is to compare the working of a simplified white box model and black-box model to predict the heating energy use of a building. The aim is to integrate these prediction models in the energy management system of SME buildings. The two models have been tested with data from a residential unit since at the time of the analysis the data of a SME building was not available. The prediction models developed have a low accuracy and in their current form cannot be integrated in an energy management system. In general, black-box model prediction obtained a higher accuracy than the white box model. The goal of the fifth model is to predict the energy use in a building using a black-box model and measure the uncertainty in the prediction. The black-box model is based on a feed-forward neural network. The model has been tested with the data of two buildings: educational and commercial buildings. The strength of the model is in the ensemble prediction and the realization that uncertainty is intrinsically present in the data as an absolute deviation. Using a rolling window technique, the model can predict energy use and uncertainty, incorporating possible building-use changes. The testing in two different cases demonstrates the applicability of the model for different types of buildings. The goal of the sixth and last model developed is to predict the energy production of PV panels in a building with the use of a black-box model. The choice for developing the model of the PV panels is based on the analysis of the main contributors of the peak energy demand and peak energy delivery in the case of the DWA office building. On a fault free test set, the model meets the requirements for a calibrated model according to the FEMP and ASHRAE criteria for the error metrics. According to the IPMVP criteria the model should be improved further. The results of the performance metrics agree in range with values as found in literature. For accurate peak prediction a year of training data is recommended in the given approach without lagged variables. This report presents the results and lessons learned from implementing white-box, grey-box and black-box models to predict energy use and energy production of buildings or of variables directly related to them. Each of the models has its advantages and disadvantages. Further research in this line is needed to develop the potential of this approach.
The maximum capacity of the road infrastructure is being reached due to the number of vehicles that are being introduced on Dutch roads each day. One of the plausible solutions to tackle congestion could be efficient and effective use of road infrastructure using modern technologies such as cooperative mobility. Cooperative mobility relies majorly on big data that is generated potentially by millions of vehicles that are travelling on the road. But how can this data be generated? Modern vehicles already contain a host of sensors that are required for its operation. This data is typically circulated within an automobile via the CAN bus and can in-principle be shared with the outside world considering the privacy aspects of data sharing. The main problem is, however, the difficulty in interpreting this data. This is mainly because the configuration of this data varies between manufacturers and vehicle models and have not been standardized by the manufacturers. Signals from the CAN bus could be manually reverse engineered, but this process is extremely labour-intensive and time-consuming. In this project we investigate if an intelligent tool or specific test procedures could be developed to extract CAN messages and their composition efficiently irrespective of vehicle brand and type. This would lay the foundations that are required to generate big data-sets from in-vehicle data efficiently.
Collaborative networks for sustainability are emerging rapidly to address urgent societal challenges. By bringing together organizations with different knowledge bases, resources and capabilities, collaborative networks enhance information exchange, knowledge sharing and learning opportunities to address these complex problems that cannot be solved by organizations individually. Nowhere is this more apparent than in the apparel sector, where examples of collaborative networks for sustainability are plenty, for example Sustainable Apparel Coalition, Zero Discharge Hazardous Chemicals, and the Fair Wear Foundation. Companies like C&A and H&M but also smaller players join these networks to take their social responsibility. Collaborative networks are unlike traditional forms of organizations; they are loosely structured collectives of different, often competing organizations, with dynamic membership and usually lack legal status. However, they do not emerge or organize on their own; they need network orchestrators who manage the network in terms of activities and participants. But network orchestrators face many challenges. They have to balance the interests of diverse companies and deal with tensions that often arise between them, like sharing their innovative knowledge. Orchestrators also have to “sell” the value of the network to potential new participants, who make decisions about which networks to join based on the benefits they expect to get from participating. Network orchestrators often do not know the best way to maintain engagement, commitment and enthusiasm or how to ensure knowledge and resource sharing, especially when competitors are involved. Furthermore, collaborative networks receive funding from grants or subsidies, creating financial uncertainty about its continuity. Raising financing from the private sector is difficult and network orchestrators compete more and more for resources. When networks dissolve or dysfunction (due to a lack of value creation and capture for participants, a lack of financing or a non-functioning business model), the collective value that has been created and accrued over time may be lost. This is problematic given that industrial transformations towards sustainability take many years and durable organizational forms are required to ensure ongoing support for this change. Network orchestration is a new profession. There are no guidelines, handbooks or good practices for how to perform this role, nor is there professional education or a professional association that represents network orchestrators. This is urgently needed as network orchestrators struggle with their role in governing networks so that they create and capture value for participants and ultimately ensure better network performance and survival. This project aims to foster the professionalization of the network orchestrator role by: (a) generating knowledge, developing and testing collaborative network governance models, facilitation tools and collaborative business modeling tools to enable network orchestrators to improve the performance of collaborative networks in terms of collective value creation (network level) and private value capture (network participant level) (b) organizing platform activities for network orchestrators to exchange ideas, best practices and learn from each other, thereby facilitating the formation of a professional identity, standards and community of network orchestrators.
Every year in the Netherlands around 10.000 people are diagnosed with non-small cell lung cancer, commonly at advanced stages. In 1 to 2% of patients, a chromosomal translocation of the ROS1 gene drives oncogenesis. Since a few years, ROS1+ cancer can be treated effectively by targeted therapy with the tyrosine kinase inhibitor (TKI) crizotinib, which binds to the ROS1 protein, impairs the kinase activity and thereby inhibits tumor growth. Despite the successful treatment with crizotinib, most patients eventually show disease progression due to development of resistance. The available TKI-drugs for ROS1+ lung cancer make it possible to sequentially change medication as the disease progresses, but this is largely a ‘trial and error’ approach. Patients and their doctors ask for better prediction which TKI will work best after resistance occurs. The ROS1 patient foundation ‘Stichting Merels Wereld’ raises awareness and brings researchers together to close the knowledge gap on ROS1-driven oncogenesis and increase the options for treatment. As ROS1+ lung cancer is rare, research into resistance mechanisms and the availability of cell line models are limited. Medical Life Sciences & Diagnostics can help to improve treatment by developing new models which mimic the situation in resistant tumor cells. In the current proposal we will develop novel TKI-resistant cell lines that allow screening for improved personalized treatment with TKIs. Knowledge of specific mutations occurring after resistance will help to predict more accurately what the next step in patient treatment could be. This project is part of a long-term collaboration between the ROS1 patient foundation ‘Stichting Merels Wereld’, the departments of Pulmonary Oncology and Pathology of the UMCG and the Institute for Life Science & Technology of the Hanzehogeschool. The company Vivomicx will join our consortium, adding expertise on drug screening in complex cell systems.
