EX-DSS: An Explorative Decision Support System for Designing and Deploying Smart Plug Forecasting Pipelines
Year: 2024
Type: conference-paper
Abstract: Artificial Intelligence pipelines are increasingly used to address specific challenges, such as forecasting smart plug loads.Smart plugs, which remotely control various appliances, can significantly reduce energy consumption in commercial buildings by about 20% when effectively scheduled using AI techniques.Designing these AI pipelines involves numerous steps and variables, requiring collaboration and shared knowledge among designers.A Decision Support System (DSS) can facilitate this process.This paper introduces the Explorative Decision Support System (EX-DSS), which extends the classical DSS framework.The EX-DSS integrates an Explorative Management Subsystem to provide project-specific recommendations and a Data Quality (DQ) module to validate user inputs, ensuring clarity and enhancing information sharing.The EX-DSS architecture framework was tested through a software prototype designed to create AI pipelines for forecasting smart plug loads.The study found that using the EX-DSS improves the quality of suggestions, making them more problem-specific and resulting in a more personalized and meaningful user experience, with a significant potential to reduce energy consumption in commercial buildings.
Authors: Giulia Rinaldi, Lola Botman, Oscar Agudelo, Bart De Moor
Institution: KU Leuven
Language: English
Subfield: Management Information Systems
Domain: Social Sciences
Open Access status: hybrid
Awards: G2115076930, G2998977510, G338995740, G434337789, G4466228027, G4599083061, G4869584417, Innovative research and valorization of plainchant through digital technology (THE SOUND OF MUSIC)., Direct detection and identification of neuro-oncology markers in brain tumours, A system identification framework for globally optimal models.
OpenAlex ID: W4404719984