# Power Systems Data Fusion based on Belief Propagation

## TL;DR

This paper introduces a probabilistic graphical model framework for power systems data fusion, enabling integration of heterogeneous data sources and distributed inference to improve grid state estimation, demonstrated on a standard test case.

## Contribution

It proposes a novel, flexible data fusion framework based on belief propagation for power systems, extending traditional state estimation methods.

## Key findings

- Efficient distributed inference algorithm derived.
- Framework successfully applied to quantify distributed solar energy.
- Numerical simulations validate the approach on IEEE 14-bus test case.

## Abstract

The increasing complexity of the power grid, due to higher penetration of distributed resources and the growing availability of interconnected, distributed metering devices re- quires novel tools for providing a unified and consistent view of the system. A computational framework for power systems data fusion, based on probabilistic graphical models, capable of combining heterogeneous data sources with classical state estimation nodes and other customised computational nodes, is proposed. The framework allows flexible extension of the notion of grid state beyond the view of flows and injection in bus-branch models, and an efficient, naturally distributed inference algorithm can be derived. An application of the data fusion model to the quantification of distributed solar energy is proposed through numerical examples based on semi-synthetic simulations of the standard IEEE 14-bus test case.