Although the accuracy of short-term prediction of building-integrated photovoltaics is essential to making an optimal decision on the management of the generated electricity, the weather forecasting service in many countries provides insufficient features for improving the prediction accuracy of the photovoltaics power output. This study suggests a machine learning model incorporated with feature engineering to improve the prediction performance of day-ahead hourly power outputs using a simple weather forecast service. A new synthetic feature, the modified sky condition, is derived to infer onsite sky condition and solar irradiation, which is not supported by the typical weather forecasting services. It evaluated the prediction performance with different training and hyper-parameter conditions for 60 days. By using the derived modified sky condition, the model outperformed other predictor configurations in most daily sky conditions; particularly, the accuracy improved by more than 50% on overcast days compared to when it used the original weather forecasting service data. The result demonstrates the feasibility and ability of the model to enable more efficient energy management of building-integrated photovoltaic power output in buildings without an onsite weather station, thus contributing toward the optimized dispatch of the integrated electricity energy storage system and other distributed energy resources.

Matrix Product States (MPSs) have become an indispensable symmetry-based representation for simulating quantum systems on near-term hardware by constraining entanglement entropy through a fixed bond dimension $\mathsf{\chi }$. This study identifies a critical “rank explosion” phenomenon that destabilizes this low-rank manifold during conditional quantum diffusion processes. We empirically demonstrate that the introduction of conditional guidance—essential for semantic control—injects global correlations that drive the effective Schmidt rank to increase by $4\times$ (from $\mathsf{\chi }=4$ to $16$), saturating the simulation limits and necessitating quantum circuits with approximately $1.8\times {10}^3$ Controlled-NOT (CNOT) gates. Such circuit depths fundamentally exceed the operational coherence budgets of Noisy Intermediate-Scale Quantum (NISQ) devices. To mitigate this structural instability, we propose Rank-Aware Conditional Synthesis (RACS), a sampling framework that maintains the latent trajectory within a prescribed MPS manifold through step-wise manifold projection and time-shift error correction. Experimental results on real-world semantic data reveal that RACS reduces reconstruction error, or Mean Squared Error (MSE) by 30.8% and enhances latent trajectory smoothness by 36.8% compared to conventional post hoc truncation. At a fixed hardware-efficient rank of $\mathsf{\chi }=4$, RACS achieves a +4.8% fidelity gain and exhibits superior robustness against depolarizing noise. By resolving the tension between conditional expressivity and entanglement constraints, RACS provides a principled, hardware-aware methodology for high-fidelity quantum generative modeling.