Stochastic programming (SP) is a powerful framework for decision-making under uncertainty, but its practical adoption in industry is often hindered by the difficulty in understanding the causal relationships that drive optimal solutions. In the two-stage SP, strategic first-stage decisions are coupled with operational second-stage recourse decisions. When the number of scenarios under consideration is large, understanding the direct link between the uncertainty realization and optimal recourse strategy becomes computationally and cognitively demanding. Common approaches to improve interpretability include trained classification trees or scenario reduction, replacing the large scenario set with a representative subset. This is often achieved through post-hoc clustering (e.g., k-means) based on uncertainty realizations or optimal recourse decisions. While useful, these methods only provide a statistical approximation of the solution space and may fail to reveal the underlying structural properties of the recourse problem that drive optimal first-stage decisions. This work introduces a novel, deterministic approach to explainability using multiparametric programming (mp) within a Benders decomposition framework. We reformulate the recourse subproblem as a multiparametric linear program, generating an explicit map of Critical Regions (CRs), which are polyhedral partitions of the uncertainty space. This allows us to cluster scenarios analytically rather than statistically. We demonstrate this methodology on a supply chain planning under demand uncertainty. Our results show that 100 stochastic scenarios map to exactly six critical region clusters. This mapping allows us to explain optimal capacity planning decisions as a precise trade-off between specific operational modes, providing a fully transparent interpretation of the stochastic solution.
The rapid growth of data centers (DCs), driven by artificial intelligence and cloud computing, presents a critical resource challenge for urban infrastructure planning across the water-energy-carbon nexus. Traditional energy models often treat DC integration merely as an isolated electrical load, failing to capture weather-dependent cooling demands and the resulting "burden-shifting" between direct on-site water consumption and the indirect water footprint of the regional grid. To bridge this gap, this study introduces a multi-scale mixed-integer linear programming (MILP) optimization framework for urban capacity expansion planning that explicitly integrates hourly climate data with the Power Usage Effectiveness (PUE) and Water Usage Effectiveness (WUE) of distinct DC cooling architectures. Applied to a representative urban microgrid, the model simulates a multi-year horizon at an hourly resolution to evaluate two contrasting DC cooling strategies: evaporative cooling and closed-loop air chillers. Our results reveal a critical trade-off: optimizing exclusively for zero on-site water use via air chillers inadvertently shifts the resource burden upstream to the regional electrical grid, demanding substantial increases in low-carbon generation, energy storage, and total infrastructure costs. Ultimately, moving beyond facility-specific metrics to evaluate holistic, system-wide Pareto trade-offs is essential for developing sustainable urban energy strategies.