Energy Modelling and Forecasting for an Underground Agricultural Farm using a Higher Order Dynamic Mode Decomposition Approach

TL;DR

This paper introduces a higher order dynamic mode decomposition (HODMD) method to model, analyze, and forecast energy behavior in an underground urban farm, effectively handling noisy and complex environmental data for predictive purposes.

Contribution

The paper applies HODMD to environmental data from an underground farm, demonstrating its ability to identify interpretable modes and accurately forecast energy behavior in complex, noisy conditions.

Findings

Identified three physically-interpretable mode pairs governing environmental behavior.

Successfully reconstructed and forecasted environmental data using a reduced-order model.

HODMD proved to be a robust and semi-automatic approach for predictive modeling in digital twins.

Abstract

This paper presents an approach based on higher order dynamic mode decomposition (HODMD) to model, analyse, and forecast energy behaviour in an urban agriculture farm situated in a retrofitted London underground tunnel, where observed measurements are influenced by noisy and occasionally transient conditions. HODMD is a data-driven reduced order modelling method typically used to analyse and predict highly noisy and complex flows in fluid dynamics or any type of complex data from dynamical systems. HODMD is a recent extension of the classical dynamic mode decomposition method (DMD), customised to handle scenarios where the spectral complexity underlying the measurement data is higher than its spatial complexity, such as is the environmental behaviour of the farm. HODMD decomposes temporal data as a linear expansion of physically-meaningful DMD-modes in a semi-automatic approach, using a time-delay embedded approach. We apply HODMD to three seasonal scenarios using real data measured by sensors located at at the cross-sectional centre of the the underground farm. Through the study we revealed three physically-interpretable mode pairs that govern the environmental behaviour at the centre of the farm, consistently across environmental scenarios. Subsequently, we demonstrate how we can reconstruct the fundamental structure of the observed time-series using only these modes, and forecast for three days ahead, as one, compact and interpretable reduced-order model. We find HODMD to serve as a robust, semi-automatic modelling alternative for predictive modelling in Digital Twins.