SEED: Public Energy and Environment Dataset for Optimizing HVAC Operation in Subway Stations

TL;DR

This paper introduces SEED, a comprehensive public dataset capturing environmental, HVAC, and passenger flow data from Beijing subway stations to facilitate energy optimization research.

Contribution

The paper provides the first detailed public dataset for subway station environments and HVAC systems, enabling more efficient analysis and policy evaluation.

Findings

Initial investigation into HVAC energy disaggregation

Analysis of thermal environment signatures

Correlation between passenger flow and HVAC energy use

Abstract

For sustainability and energy saving, the problem to optimize the control of heating, ventilating, and air-conditioning (HVAC) systems has attracted great attentions, but analyzing the signatures of thermal environments and HVAC systems and the evaluation of the optimization policies has encountered inefficiency and inconvenient problems due to the lack of public dataset. In this paper, we present the Subway station Energy and Environment Dataset (SEED), which was collected from a line of Beijing subway stations, providing minute-resolution data regarding the environment dynamics (temperature, humidity, CO2, etc.) working states and energy consumptions of the HVAC systems (ventilators, refrigerators, pumps), and hour-resolution data of passenger flows. We describe the sensor deployments and the HVAC systems for data collection and for environment control, and also present initial investigation for the energy disaggregation of HVAC system, the signatures of the thermal load, cooling supply, and the passenger flow using the dataset.