A Modeling–Optimization–Validation Framework for Digital Transformation Decisions in Socio‐Technical Systems: Evidence From Wastewater Treatment Projects

ABSTRACT

Managers of socio‐technical systems (STSs) lack quantitative tools to optimize digital technology (DT) selection. This study bridges this gap by developing a unified modeling–optimization–validation decision‐making framework, positioned as an upstream, preplanning tool complementary to operational digital twins. First, a time‐varying network model is constructed with explicit mathematical definitions for task‐information dynamics. Second, DT selection is formulated as a multiple‐choice knapsack problem (MCKP) and solved using a genetic algorithm (GA) with formally defined fitness functions and constraints. Third, numerical simulations validate the approach. A case study of a wastewater treatment project demonstrates that the optimized DT portfolio yields an average efficiency improvement of 27.9% (calculated based on node‐level productive and cost efficiency). This framework provides a transferable, quantitative basis for designing digital transformation roadmaps, offering a lower‐effort alternative for initial investment prioritization compared to high‐frequency operational calibration in traditional digital twins.