Boyu Yao

Fan Wang, Keli Wang, Boyu Yao

Recent advances in digitization have led to the availability of multivariate time series data in various domains, enabling real-time monitoring of operations. Identifying abnormal data patterns and detecting potential failures in these scenarios are important yet rather challenging. In this work, we propose a novel unsupervised anomaly detection method for time series data. The proposed framework jointly learns the observation model and the dynamic model, and model uncertainty is estimated from normal samples. Specifically, a long short-term memory (LSTM)-based encoder-decoder is adopted to represent the mapping between the observation space and the latent space. Bidirectional transitions of states are simultaneously modeled by leveraging backward and forward temporal information. Regularization of the latent space places constraints on the states of normal samples, and Mahalanobis distance is used to evaluate the abnormality level. Empirical studies on synthetic and real-world datasets demonstrate the superior performance of the proposed method in anomaly detection tasks.

Boyu Yao, Yury Dvorkin

Power system expansion depends on the equipment required to connect, convert, regulate, and condition electricity, yet grid-supporting equipment (GSE) is rarely modeled as an explicit constraint. We develop a framework integrating dynamic stock-flow modeling, bill-of-materials accounting, multi-regional supply-use analysis, and expansion optimization to quantify GSE deployment requirements and upstream material dependence. Because manufacturing data are often fragmented or proprietary, we use critical material requirements as a physically grounded proxy for GSE supply constraints. In a U.S. case study, GSE shortages reach 269.6--274.1 GVA (28.5%--28.6%) by 2030 under high-growth conditions. Copper becomes fully binding, with steel and nickel forming additional constraints. Trade disruption intensifies shortages, while grid-enhancing technologies provide limited relief. These results show that grid expansion depends on the timely manufacturability, replacement, and material support of GSE, motivating planning frameworks that explicitly incorporate deliverability, supply chain exposure, and resilience strategies.

Boyu Yao, Andrey Bernstein, Yury Dvorkin

Rising electricity demand underscores the need for secure and reliable generation expansion planning that accounts for upstream supply chain constraints. Traditional models often overlook limitations in materials, manufacturing capacity, lead times for deployment, and field availability, which can delay availability of planned resources and thus to threaten system reliability. This paper introduces a multi-stage supply chain-constrained generation expansion planning (SC-GEP) model that optimizes long-term investments while capturing material availability, production limits, spatial and temporal constraints, and material reuse from retired assets. A decomposition algorithm efficiently solves the resulting MILP. A Maryland case study shows that supply chain constraints shift technology choices, amplify deployment delays caused by lead times, and prompt earlier investment in shorter lead-time, low-material-intensity options. In the low-demand scenario, supply chain constraints raise investment costs by $1.2 billion. Under high demand, persistent generation and reserve shortfalls emerge, underscoring the need to integrate upstream constraints into long-term planning.