A Modified Sequence-to-point HVAC Load Disaggregation Algorithm

TL;DR

This paper introduces a modified CNN-based sequence-to-point algorithm for disaggregating HVAC loads, incorporating temperature profiles, dropout, and fine-tuning to enhance accuracy and transferability across different regions.

Contribution

The paper proposes three key modifications to the original S2P model, improving its adaptability and transferability for HVAC load disaggregation across diverse geographical areas.

Findings

The modified S2P outperforms the original in accuracy.

The model demonstrates effective transferability to new regions.

Inclusion of temperature profiles enhances disaggregation performance.

Abstract

This paper presents a modified sequence-to-point (S2P) algorithm for disaggregating the heat, ventilation, and air conditioning (HVAC) load from the total building electricity consumption. The original S2P model is convolutional neural network (CNN) based, which uses load profiles as inputs. We propose three modifications. First, the input convolution layer is changed from 1D to 2D so that normalized temperature profiles are also used as inputs to the S2P model. Second, a drop-out layer is added to improve adaptability and generalizability so that the model trained in one area can be transferred to other geographical areas without labelled HVAC data. Third, a fine-tuning process is proposed for areas with a small amount of labelled HVAC data so that the pre-trained S2P model can be fine-tuned to achieve higher disaggregation accuracy (i.e., better transferability) in other areas. The model is first trained and tested using smart meter and sub-metered HVAC data collected in Austin, Texas. Then, the trained model is tested on two other areas: Boulder, Colorado and San Diego, California. Simulation results show that the proposed modified S2P algorithm outperforms the original S2P model and the support-vector machine based approach in accuracy, adaptability, and transferability.