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

TL;DR

SplitVAEs is a decentralized framework using variational autoencoders that generates high-quality scenarios for large-scale stochastic optimization problems without requiring data centralization, preserving privacy and reducing communication costs.

Contribution

It introduces a novel decentralized scenario generation method leveraging variational autoencoders, enabling scalable and privacy-preserving data analysis in multi-stakeholder systems.

Findings

SplitVAEs accurately learn spatial and temporal dependencies.

They match the joint distribution of stakeholder data.

They outperform centralized benchmarks in robustness and efficiency.

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.