# Continually learning out-of-distribution spatiotemporal data for robust energy forecasting

arXiv: https://arxiv.org/abs/2306.06385 · HTML: https://mlsanity.com/paper/2306.06385/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 35 references that are in the map.
- First posted on arXiv 10 Jun 2023.

## Builds on (most cited first, 15 of 15)

- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [Online Learning: A Comprehensive Survey](https://mlsanity.com/paper/1802.02871/) (2018)
- [Darts: User-Friendly Modern Machine Learning for Time Series](https://mlsanity.com/paper/2110.03224/) (2021)
- [Online Deep Learning: Learning Deep Neural Networks on the Fly](https://mlsanity.com/paper/1711.03705/) (2017)
- [Learning Fast and Slow for Online Time Series Forecasting](https://mlsanity.com/paper/2202.11672/) (2022)
- [Fast Distributed Bandits for Online Recommendation Systems](https://mlsanity.com/paper/2007.08061/) (2020)
- [N-BEATS neural network for mid-term electricity load forecasting](https://mlsanity.com/paper/2009.11961/) (2020)
- [TERMCast: Temporal Relation Modeling for Effective Urban Flow Forecasting](https://mlsanity.com/paper/2011.05554/) (2020)
- [Because Every Sensor Is Unique, so Is Every Pair: Handling Dynamicity in Traffic Forecasting](https://mlsanity.com/paper/2302.09956/) (2023)
- [Pattern-based Long Short-term Memory for Mid-term Electrical Load Forecasting](https://mlsanity.com/paper/2004.11834/) (2020)
- [Predicting Flight Delay with Spatio-Temporal Trajectory Convolutional Network and Airport Situational Awareness Map](https://mlsanity.com/paper/2105.08969/) (2021)
- [Online Optimization Methods for the Quantification Problem](https://mlsanity.com/paper/1605.04135/) (2016)
- [Message Passing Neural Networks for Traffic Forecasting](https://mlsanity.com/paper/2305.05740/) (2023)

## Built on by (most cited first, 5 of 5)

- [Out-of-Distribution Generalization in Time Series: A Survey](https://mlsanity.com/paper/2503.13868/) (2025)
- [BTS: Building Timeseries Dataset: Empowering Large-Scale Building Analytics](https://mlsanity.com/paper/2406.08990/) (2024)
- [Navigating Out-of-Distribution Electricity Load Forecasting during COVID-19: Benchmarking energy load forecasting models without and with continual learning](https://mlsanity.com/paper/2309.04296/) (2023)
- [Integrating Symbolic Neural Networks with Building Physics: A Study and Proposal](https://mlsanity.com/paper/2411.00800/) (2024)
- [A Gap in Time: The Challenge of Processing Heterogeneous IoT Data in Digitalized Buildings](https://mlsanity.com/paper/2405.14267/) (2024)

## Abstract (arXiv)

Forecasting building energy usage is essential for promoting sustainability and reducing waste, as it enables building managers to optimize energy consumption and reduce costs. This importance is magnified during anomalous periods, such as the COVID-19 pandemic, which have disrupted occupancy patterns and made accurate forecasting more challenging. Forecasting energy usage during anomalous periods is difficult due to changes in occupancy patterns and energy usage behavior. One of the primary reasons for this is the shift in distribution of occupancy patterns, with many people working or learning from home. This has created a need for new forecasting methods that can adapt to changing occupancy patterns. Online learning has emerged as a promising solution to this challenge, as it enables building managers to adapt to changes in occupancy patterns and adjust energy usage accordingly. With online learning, models can be updated incrementally with each new data point, allowing them to learn and adapt in real-time. Another solution is to use human mobility data as a proxy for occupancy, leveraging the prevalence of mobile devices to track movement patterns and infer occupancy levels. Human mobility data can be useful in this context as it provides a way to monitor occupancy patterns without relying on traditional sensors or manual data collection methods. We have conducted extensive experiments using data from six buildings to test the efficacy of these approaches. However, deploying these methods in the real world presents several challenges.