While real-time data and sophisticated Reinforcement Learning (RL) approaches are emerging, logistic organizations, in particular Small and Medium-sized Enterprises (SMEs), lack the tools and expertise to effectively identify whether (parts of) their business processes are suitable for using RL and adopt these approaches in their daily practice. This paper presents the results of our efforts to design, develop, test and implement a RL-based decision support platform based on the Open Trip Model (OTM) for the logistics industry. The main contribution of this paper is a potentially generalizable platform architecture and instantiation of the following main functional components: 1) a graphical user interface to access platform services, 2) APIs to automate the data collection based on the OTM, 3) an OTM compliant data storage, 4) a repository and tool for testing multiple algorithms and perform (hyper)parameter tuning, and 5) infrastructure provisioning to run and monitor agents. The platform is complemented with RL guidelines to transfer the platform, knowledge, and practices to SMEs. The platform architecture is validated with a panel of experts and demonstrated in use in a case study at a logistics services provider. The platform demonstration and case study contribute to increasing awareness of potential applications of RL in the logistics industry. The platform provides a foundation for empirical research and experimental development of RL approaches in logistics. Future research will focus on alternative and hybrid approaches, federated learning, and incorporating data sharing concepts as part of the envisioned federated data sharing infrastructure for the Dutch logistics industry.

In the past decades, a broad range of technological innovations have helped organizations reach new levels of performance and have shaped the economies of the world and societies of the future. However, unexpected events, such as the COVID-19 pandemic and the blocking of the Suez Canal, have shown that many organizations are unprepared to deal with the impact of the disturbances that can occur. Thus, organizations are challenged to include resilience in the design of their Information Systems and Enterprise Architectures (EAs). We respond to this challange and propose a five-step method aimed to help organizations design resilient enterprise architectures to be able to better deal with (un-) expected disturbances. Our method builds upon the ‘EA resilience by design’ paradigm, combines knowledge from several domains, namely resilience, risk analysis, and EA, and leverages the ArchiMate 3.1 language to model several resilience characteristics. Using a case study at a leading manufacturing organization in the agri-food sector in Lithuania, we demonstrate the applicability of our method and draw some early lessons learned based on our very first evaluation with experts.

When aggregating logistic event data from different supply chain actors and information systems for process mining, interoperability, data loss, and data quality are common challenges. This position paper proposes and evaluates the use of the Open Trip Model (OTM) for process mining. Inspired by the current industrial use of the OTM for reporting and business intelligence, we believe that the data model of OTM can be utilized for unified storage, integration, interoperability, and querying of logistic event data. Therefore, the OTM data model is mapped to a generic event log structure to satisfy the minimum requirements for process mining. A demonstrative scenario is used to show how event data can be extracted from the OTM’s default scenario dataset to create an event log as the starting point for process mining. Thus, this approach provides a foundation for future research about interoperability challenges and unifying process mining models based on industry standards, and a starting point for developing process mining applications in the logistics industry.

The process of connecting enterprise systems and applications to digital platforms and ecosystems requires interoperability on different levels and eventually leads to the task of creating a schema mapping. At present, this task is carried out manually and prior research has proven this task difficult to automate. In this paper, we discuss the suitability of machine learning approaches to create an auto-mapping functionality, so different schemas and standards can (partially) be mapped automatically, and incorporate a symbiotic approach to improve the matching result. To the best of our knowledge, this is a new approach with potential to reduce the time needed for schema matching tasks. The main contribution of this paper is a reference architecture and prototype for smarter interoperability using a combination of automatic schema matching, based on machine learning, and intelligence amplification.

Small and Medium-sized Enterprises (SMEs) in logistics experience practical barriers when trying to use, exchange, share, and exploit real-time data in their operational processes. Such barriers include the abundance of proprietary data formats and schemes, the cost of implementing standards, the lack of trust among partners, the lack of IT expertise, and the uncertainty about benefits and return on investments. This position paper introduces the goal and proposed approach of a recently started research project that aims at lowering these barriers. The core proposition revolves around the application of a federated approach based on the concepts of the International Data Space (IDS). In this paper we present a high level architecture underlying this goal and approach. Two main components of the architecture are discussed in more detail: (1) a connector store, offering connectors to realize data exchange between heterogeneous ICT environments, and (2) an interoperability simulator, to explore collaboration opportunities prior to implementation.

Building on earlier work, this paper aims to demonstrate and discuss an instantiated architecture for situation-aware logistics in an operational environment using smart returnable assets. The demonstration is based on a motivation scenario focusing on exception management. The system outline and its components, interfaces, and enabling technologies are described and linked to the different layers of the architecture. This paper documents and illustrates the use of the system with detailed models and screenshots. Earlier work is extended using business rules to identify and quantify exceptions and potential disruptions. Specifically, it is shown how shipment data are enhanced with data from IoT sensors of smart returnable assets to provide situation-aware decision support based on data analytical methods. This demonstration provides scholars and practitioners, active in the fields of enterprise computing, insights into the concepts, models and engineering technologies used to implement an architecture for situation-aware logistics. The instantiated architecture provides a rich testbed for experiments, measurements, and incorporate the ideas promoted by the international data space initiative. An online recording is available to support the demonstration and ignite discussion about the potential of IoT technologies and future research directions in pursuit of the smart logistics vision.

This review paper aims to explore state-of-the-art research and scientific literature about Enterprise Architecture (EA) resilience. Based on a systematic literature review, 850 articles have been subjected to evaluation for relevance. Based on the findings in 58 selected papers, we conclude that the field of EA resilience is still in its infancy. We identified several definitions and classified six types of resilience measures, based on information type (qualitative/quantitative), the source of the disruption (internal/external), and the duration of the resilience (short-term/long-term). Based on the review, we found 19 metrics that are candidates for EA practitioners to consider for the design of measurement and assessment methods for EA resilience. In addition, we identified relevant research from Information Systems sub-domains and other sciences that can be incorporated to create a holistic view on EA resilience. Based on published definitions of resilience in the selected papers, we propose a definition of the concept of EA resilience. This definition is validated using expert opinion and creates a starting point for reasoning about EA resilience and future research.

This is the public final report (in Dutch) of the Autonomous Logistics Miners for Small & Mediumsized Businesses project, a 2-year research project conducted within the Logistics Top Sector on based on the TKI Toeslag Call. This project contributes to strengthening the competitive position of SMEs by investigating the use of smart data mining agents in logistics processes and helping professionals make data-driven decisions and automate routine tasks. This way smart data mining agents help SMEs respond quickly to disruptive events, such as delays and changing trends in supply and demand, and provide insights into performance and efficiency.

The goal of this white paper is to provide guidance to the Topsector Logistics implementation program on the data sharing infrastructure as part of the priority theme ‘data driven logistics’, by:

• describing the current developments in data sharing policy making and data sharing architectures,
• identifying a structure and portfolio of key data sharing functions to be realized as generic, re-usable, services (building blocks), based on a representative set of use cases for the three application areas, and
• providing a development roadmap as input for the implementation program.

This white paper may help logistics policy makers in defining innovation activities, the logistics sector in its quest to stay competitive and become more sustainable and logistics organizations to position themselves in the digital transformation towards the data driven ecosystem This white paper originates in the DL4LD research project. It is the result of a collaboration effort between TNO, DL4LD project partners, the University of Twente, with active involvement of TKI Dinalog. Principal researchers have contributed from the DL4LD, the CLiCKS and the ICCOS projects.

Purpose – The purpose of this research paper is 1) to analyze Logistics Hotspots and Regional Logistics Ecosystems in the Netherlands and 2) investigate how the Logistics Hotspot Port of Twente can double stitch the triple helix approach to 2a) develop its Regional Logistics Ecosystem and 2b) align its business plan with the 2050 ambition and the action agenda for 2020-2023 of the Dutch Topsector Logistics. Design/methodology/approach – The methodological approach undertaken in this study is based on a literature review, desk research, data from the annual rankings of Dutch Logistics Hotspots, the framework for Regional Logistics Ecosystems, interviews with 12 board members and 33 members of Port of Twente and design workshops with 25 community members of Port of Twente. Results/findings – Contrasting the extensive literature about business ecosystems, little scientific literature is available about Logistics Hotspots and Regional Logistics Ecosystems. Based on available data from the annual rankings of 28 Logistics Hotspots in the Netherlands, 27 Regional Logistics Ecosystems are identified, analyzed and classified as business-, innovation-, entrepreneurial- and/or knowledge ecosystem. More specific, Port of Twente is analyzed based on the framework for Regional Logistics Ecosystems and action agenda for 2020-2023 of the Topsector Logistics. The insights are embedded in the business development plan of Port of Twente and a technology roadmap is created based on the clustering of 17 innovation projects as a starting point to establish a learning community. Research limitations/implications – The desk research is based on published rankings and available materials from websites. Due to the absence of public available research data and practical constraints, the classification of ecosystems is based on 4 main types of ecosystems. Further empirical research can be conducted based on the theoretical framework of Scaringella and Radziwon to map the logistics innovation system in the Netherlands. Practical implications – The business development plan and technology roadmap provides Port of Twente a starting point for further development. In a broader sense, the results of this study provide important insights, recommendations and guidance to connect Logistics Hotspots and Regional Logistics Ecosystems to the Topsector Logistics 2050 ambition and action agenda for 2020-2023. Originality/value – The study contributes to better understanding of Logistics Hotspots and Regional Logistics Ecosystems in the Netherlands. The work presented here provides one of the first investigations about the alignment of the Dutch Topsector Logistics 2050 ambition and action agenda for 2020-2023 with Logistics Hotspots and Regional Logistics Ecosystems utilizing insights from both science and industry. The contents of this work are considered valuable for policy makers, logistics entrepreneurs, researchers active in triple helix projects and professionals responsible for strategy and technology development in Logistics Hotspots and Regional Logistics Ecosystems.

Disruptions and exceptions are an important source of risks in logistics, as far as the planning of transportation services is concerned. Failing to rapidly react on and handle such events may lead to serious depreciation of the transported cargo and reputation damage. The Internet of Things seems to be the technology capable of providing the tools required to detect exceptions nearly real-time. However, currently, there is little research on how to enhance the detected exceptions with related information from internal or external sources. Furthermore, most exception detection capabilities rely on experience and not much research exist on how to improve the accuracy of using third-party knowledge. In this paper, we propose a reference architecture for situation-aware logistics. The architecture specification follows the key principles derived from an extensive requirements analysis, the state of the art literature, and the ideas promoted by the Industrial Data Space initiative. The proposed architecture has been instantiated and tested by means of a prototype designed for the case of temperature-controlled transportation services.

The aim of this doctoral consortium paper is to introduce my doctoral research proposal in the field of enterprise computing. The scientific problem that I address in my research is the limited usage of real-time data, originating from Industry 4.0 (I4.0) technologies (e.g. smart IoT devices and sensors), by Small-and Medium sized Enterprises (SMEs) in the logistics industry. I argue that the development of an industry platform for real-time data streaming and analytics would allow SMEs to benefit from such data and help them streamline their operational processes and overall performance. The main contribution of my research is a reference architecture for such a platform, geared for the needs of SMEs, and incorporating: 1) a logistics canonical data model to collect and harmonize I4.0 data, 2) an automatic schema matcher to map SME data to the logistics canonical data model, 3) autonomous data mining agents, 4) an adoption strategy based on the concept of intelligence amplification and 5) key performance indicators to measure adoption effects on operational and decisional performance.

In logistics, questions as “Where is my container?” and “When does my container arrive?” can often not be answered with sufficient precision, which restricts the ability of logistics service providers to be efficient. Since logistics is complex and often involves multiple transportation modes and carriers, improving efficiency and saving costs in the supply chain requires communication between the different parties and the usage of real-time data is critical. Currently, logistics service providers (LSPs) use real-time data to a very limited extent, mainly for tracking the progress of a specific part of a given shipment. This data is retrieved manually from a number of websites and sharing with other actors is not even considered. This leads to lack of end-to end visibility and delays in planning. This research proposes an architecture and a common data model for an integration platform that allows the automated collection of real time container tracking data enabling LSPs to plan more efficient. Currently, there is no common data model available that contains all the information required and enables LSPs to track their shipments real-time. The common data model is designed via a bottom-up approach using results of interviews, observations at different logistics service providers, analyses of open data on websites, and serves the information needs of the business processes involving such data. The model is also validated against industry standards. Based on the proposed architecture a prototype was built that is tested in real operating conditions with a fourth party logistics company.