A Data-Driven Simulation Framework for Sustainable Design: Forecasting Wind Energy Trends in Taiwan

This study proposes a data-driven simulation framework for forecasting wind-energy trends in Taiwan and examines how computational prediction can support sustainable design education. The model, implemented in MATLAB, integrates deterministic sinusoidal functions with stochastic variability to emulate seasonal and diurnal wind patterns, producing interpretable and reproducible time-series outputs. Across a three-year simulation span, results illustrate an upward trend in modeled power generation and a reduction in daily fluctuation, suggesting improvements in turbine stability and system efficiency under assumed scenarios. Beyond technical forecasting, the study positions simulation as a design-oriented interpretive medium. Building on prior work in sustainability education, data visualization, and experiential learning, the framework demonstrates how learners can analyze temporal dynamics, recognize long-range energy trajectories, and engage with uncertainty through visual exploration. This dual function-as analytical tool and interpretive interface-highlights how predictive modeling can bridge engineering reasoning with design understanding. By translating complex environmental change into accessible visual forms, the framework supports the development of sustainability literacy and enriches interdisciplinary dialogue around renewable-energy futures.