SplitVAEs: Decentralized scenario generation from siloed data for stochastic optimization problems

TL;DR

SplitVAEs address the challenge of generating high-fidelity scenarios for stochastic optimization without centralizing siloed data. The framework combines edge-level autoencoders with a server-level variational autoencoder, enabling decentralized training through bi-directional backpropagation and distributed memory primitives. Empirical results across diverse datasets show SplitVAEs match centralized baselines in statistical fidelity while significantly reducing data transmission and handling heterogeneous data dimensions. This privacy-preserving approach offers a scalable alternative for scenario generation in multi-stakeholder infrastructure networks, facilitating faster, cross-domain stochastic optimization without data sharing.

Abstract

Stochastic optimization problems in large-scale multi-stakeholder networked systems (e.g., power grids and supply chains) rely on data-driven scenarios to encapsulate complex spatiotemporal interdependencies. However, centralized aggregation of stakeholder data is challenging due to the existence of data silos resulting from computational and logistical bottlenecks. In this paper, we present SplitVAEs, a decentralized scenario generation framework that leverages variational autoencoders to generate high-quality scenarios without moving stakeholder data. With the help of experiments on distributed memory systems, we demonstrate the broad applicability of SplitVAEs in a variety of domain areas that are dominated by a large number of stakeholders. Our experiments indicate that SplitVAEs can learn spatial and temporal interdependencies in large-scale networks to generate scenarios that match the joint historical distribution of stakeholder data in a decentralized manner. Our experiments show that SplitVAEs deliver robust performance compared to centralized, state-of-the-art benchmark methods while significantly reducing data transmission costs, leading to a scalable, privacy-enhancing alternative to scenario generation.

Figures (10)

• Figure 1: Scenario generation for stochastic optimization.
• Figure 2: The learning paradigm of SplitVAEs.
• Figure 3: Embedding distributions between observed data and generated scenarios using different methods across four cases.
• Figure 4: Comparison of centroids between observed and generated data across four datasets.
• Figure 5: Comparison of autocorrelations between observed and generated data across four datasets.