Analytics and Decision Support for Green IS and Sustainability Applications

Permanent URI for this collection


Recent Submissions

Now showing 1 - 8 of 8
  • Item
    Understanding the Impact of Sustainability and CSR Information in D2C Online Shops on Consumer Attitudes and Behavior – A Literature Review
    ( 2021-01-05) Schacker, Maximilian ; Stanoevska-Slabeva, Katarina
    Many brands nowadays use direct-to-consumer channels such as proprietary online shops, in order to provide information related to their sustainability and CSR initiatives and to increase consumers’ perceptions of legitimacy of the company and its products. However, so far little is known about the effects of such information on consumer attitudes and behavior. This implies that the true benefit of S/CSR initiatives is currently not well understood by most companies and resource allocation in this area may be distorted. Therefore, in this literature review we consolidate and map existing research that can inform our understanding of this phenomenon. By analyzing a sample of 46 papers we find that research on the topic in a direct-to-consumer context is sparse, but that theories and empirical evidence from related contexts can help us grasp the issue to some extent.
  • Item
    Industrial Symbiosis Waste Exchange Identification and Optimization
    ( 2021-01-05) Curri, Danielle ; Aziz, Tarek ; Baugh, John ; Johnson, Jeremiah
    Industrial symbiosis is the concept that waste from industrial processes can be diverted and then reused as inputs into co-located industrial entities. While research to date has identified successful examples of industrial symbiosis and characterized formation processes, little is known about how new eco-industrial parks can be designed and their performance optimized. In this paper, we describe how industrial symbiosis can be modeled and optimized during the development phase to assist in the creation of eco-industrial parks. We present a database framework, waste exchange identification algorithm, and Python-based optimization system that generates a mixed-integer linear programming model to minimize the amount of non-recycled waste produced. We illustrate the functionality of the approach on three test cases that demonstrate increasing levels of complexity. The optimization model can also accommodate multiple objectives, allowing further exploration of the benefits of industrial symbiosis at the design stage.
  • Item
    Green User Electronics Lifecycle Behavior and Planning Mechanisms
    ( 2021-01-05) Li, Yaojie ; Wang, Xuan ; Stafford, Tom ; Javadi Khasraghi, Hanieh
    This paper seeks to understand general user intentions toward engaging in green information technology (IT) behaviors, and in engaging with the consumer electronics lifecycle, which includes not only adoption and use, but also disposal. Based upon an extended planned behavior theoretical framework, our study suggests that what we call “eco-belief” among technology users can determine eco-attitude, subjective norms, and perceived behavioral controls related to the life cycle process, thus shaping green user behavior. Also, eco-knowledge appears to be important in changing user’s attitudes and intentions to perform green behaviors. This study also revisited relevant green IT and green Information Systems (IS) literature and viewpoints while providing possible research directions based on its analysis results.
  • Item
    Developing a Green IS to support the move to eco-effective packaging: A Design Science Research study
    ( 2021-01-05) Burton, Keith ; O'Raghallaigh, Paidi ; Nagle, Tadhg
    United Nations Sustainable Development Goal (UN SDG) 12.6 aims to “encourage companies, especially large and transnational companies, to adopt sustainable practices and to integrate sustainability information into their reporting cycle” [43]. Using Design Science Research, GReenstreets Integrated Packaging Sustainability reporting system (“GRIPS”) is an expository artefact built using the BAO design theory for green information systems (Green IS) (c.f. Recker) [34]. The artefact aims to support organizations in overcoming sustainability challenges by providing information to help them make effective decisions around packaging sustainability and to facilitate the move from eco-efficiency to eco-effectiveness practices. This study adds to practice by helping companies to act, measure and monitor the move towards eco-effective packaging. It adds to research by providing an expository artefact based on the design theory for Green IS proposed by Recker [34].
  • Item
    An Approach for Weed Detection Using CNNs And Transfer Learning
    ( 2021-01-05) Ofori, Martinson ; El-Gayar, Omar
    To prevent yield losses, it is critical to eliminate competition between food crops and weeds at the onset of plant growth. While uniform spraying of herbicides can be economically and environmentally inefficient, site-specific weed management (SSWM) counteracts this by reducing the amount of chemical application with localized spraying of weed species. Past research on weed detection in SSWM has used a large deep convolutional neural network (DCNN) for weed detection. These models are, however, computationally expensive and prone to overfitting on smaller datasets. In this paper, we propose an approach to detecting weeds amongst plant seedlings using transfer learning in a small network. Our approach combines the mobile-sized EfficientNet with transfer learning to achieve up to 95.44% classification accuracy on plant seedlings. Due to the robustness of transfer learning methods, this approach would be beneficial in improving both the classification accuracy and generalizability of current weed detection methods.
  • Item
    An adaptive scheduling framework for the dynamic virtual machines placement to reduce energy consumption in cloud data centers
    ( 2021-01-05) Nahhas, Abdulrahman ; Cheyyanda , Jahnavi Thimmaiah ; Turowski , Klaus
    Cloud computing has revolutionized the IT industry through its on-demand provisioning of virtualized resources through the internet. Although it relies on sharing of resources to improve the performance of datacenters, it has increased the complexity of IT systems in recent years. To meet the market requirements, cloud providers are expanding their datacenters with a large number of servers leading to high energy consumption and therefore, increasing the carbon footprint. Environmental impact and rapidly surging energy costs have become a major concern for both the government bodies and the IT service providers. In this paper, we propose a genetic algorithm based hybrid load management strategy which uses multiple existing VM allocation policies to minimize the energy consumption, Service Level Agreement (SLA) violations and number of VM migrations. The presented solution approach is evaluated on CloudSim Plus simulation framework using the well known PlanetLab workload. The results obtained from the experiments show substantial improvement in energy consumption in comparison to the individual approaches while maintaining the performance constraints.
  • Item
    AI-based Decision Support for Sustainable Operation of Electric Vehicle Charging Parks
    ( 2021-01-05) Baumgarte, Felix ; Dombetzki, Luca ; Kecht, Christoph ; Wolf, Linda ; Keller, Robert
    The widespread adoption of electric vehicles makes investments in charging parks both immediate and necessary to lower range anxiety and allow longer trips. However, many charging park operators struggle with sustainable and profitable operation due to high fees on peak loads and volatile availability of renewable energy. Smart charging strategies may enable such operation, but the computational complexity of most available algorithms increases significantly with the number of charging points. Thus, operators of larger charging parks need information systems that provide real-time decision support without immense cost for computation. This paper presents a model that uses recent methods from the field of Reinforcement Learning. Our model is trained on a charging park simulation with realworld data on highway traffic and day ahead energy prices. The results indicate that Reinforcement Learning is a feasible solution to improve the sustainable and profitable operation of large electric vehicle charging parks.
  • Item