Transfer Learning in Transformer-Based Demand Forecasting For Home Energy Management System

• URL: http://arxiv.org/abs/2310.19159v1
• Date: Sun, 29 Oct 2023 21:19:08 GMT
• Title: Transfer Learning in Transformer-Based Demand Forecasting For Home Energy Management System
• Authors: Gargya Gokhale, Jonas Van Gompel, Bert Claessens, Chris Develder
• Abstract summary: We analyze how transfer learning can help by exploiting data from multiple households to improve a single house's load forecasting. Specifically, we train an advanced forecasting model using data from multiple different households, and then finetune this global model on a new household with limited data. The obtained models are used for forecasting power consumption of the household for the next 24 hours(day-ahead) at a time resolution of 15 minutes.
• Score: 4.573008040057806
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Increasingly, homeowners opt for photovoltaic (PV) systems and/or battery storage to minimize their energy bills and maximize renewable energy usage. This has spurred the development of advanced control algorithms that maximally achieve those goals. However, a common challenge faced while developing such controllers is the unavailability of accurate forecasts of household power consumption, especially for shorter time resolutions (15 minutes) and in a data-efficient manner. In this paper, we analyze how transfer learning can help by exploiting data from multiple households to improve a single house's load forecasting. Specifically, we train an advanced forecasting model (a temporal fusion transformer) using data from multiple different households, and then finetune this global model on a new household with limited data (i.e. only a few days). The obtained models are used for forecasting power consumption of the household for the next 24 hours~(day-ahead) at a time resolution of 15 minutes, with the intention of using these forecasts in advanced controllers such as Model Predictive Control. We show the benefit of this transfer learning setup versus solely using the individual new household's data, both in terms of (i) forecasting accuracy ($\sim$15\% MAE reduction) and (ii) control performance ($\sim$2\% energy cost reduction), using real-world household data.

Related papers

• AI-Powered Predictions for Electricity Load in Prosumer Communities [0.0]
  We present and test artificial intelligence powered short-term load forecasting methodologies. Results show that the combination of persistent and regression terms (adapted to the load forecasting task) achieves the best forecast accuracy.
  arXiv  Detail & Related papers  (2024-02-21T12:23:09Z)
• Benchmarks and Custom Package for Energy Forecasting [55.460452605056894]
  Energy forecasting aims to minimize the cost of subsequent tasks such as power grid dispatch. In this paper, we collected large-scale load datasets and released a new renewable energy dataset. We conducted extensive experiments with 21 forecasting methods in these energy datasets at different levels under 11 evaluation metrics.
  arXiv  Detail & Related papers  (2023-07-14T06:50:02Z)
• Comparative Analysis of Time Series Forecasting Approaches for Household Electricity Consumption Prediction [3.7458346891274013]
  We use Weka, a data mining tool, to first apply models on hourly and daily household energy consumption datasets available from Kaggle data science community. Secondly, we also implemented time series forecasting models, ARIMA and VAR, in python to forecast household energy consumption of selected South Korean households with and without weather data. Our results show that the best methods for the forecasting of energy consumption prediction are Support Vector Regression followed by Multilayer Perceptron and Gaussian Process Regression.
  arXiv  Detail & Related papers  (2022-07-03T12:16:54Z)
• Appliance Level Short-term Load Forecasting via Recurrent Neural Network [6.351541960369854]
  We present an STLF algorithm for efficiently predicting the power consumption of individual electrical appliances. The proposed method builds upon a powerful recurrent neural network (RNN) architecture in deep learning.
  arXiv  Detail & Related papers  (2021-11-23T16:56:37Z)
• Advanced Statistical Learning on Short Term Load Process Forecasting [13.466565318976887]
  Short Term Load Forecast (STLF) is necessary for effective scheduling, operation optimization trading, and decision-making for electricity consumers. We propose different statistical nonlinear models to manage these challenges of hard type datasets and forecast 15-min frequency electricity load up to 2-days ahead.
  arXiv  Detail & Related papers  (2021-10-19T12:32:40Z)
• Efficient pre-training objectives for Transformers [84.64393460397471]
  We study several efficient pre-training objectives for Transformers-based models. We prove that eliminating the MASK token and considering the whole output during the loss are essential choices to improve performance.
  arXiv  Detail & Related papers  (2021-04-20T00:09:37Z)
• The impact of online machine-learning methods on long-term investment decisions and generator utilization in electricity markets [69.68068088508505]
  We investigate the impact of eleven offline and five online learning algorithms to predict the electricity demand profile over the next 24h. We show we can reduce the mean absolute error by 30% using an online algorithm when compared to the best offline algorithm. We also show that large errors in prediction accuracy have a disproportionate error on investments made over a 17-year time frame.
  arXiv  Detail & Related papers  (2021-03-07T11:28:54Z)
• Investigating Underlying Drivers of Variability in Residential Energy Usage Patterns with Daily Load Shape Clustering of Smart Meter Data [53.51471969978107]
  Large-scale deployment of smart meters has motivated increasing studies to explore disaggregated daily load patterns. This paper aims to shed light on the mechanisms by which electricity consumption patterns exhibit variability.
  arXiv  Detail & Related papers  (2021-02-16T16:56:27Z)
• Distributed Deep Reinforcement Learning for Intelligent Load Scheduling in Residential Smart Grids [9.208362060870822]
  We propose a model-free method for the households which works with limited information about the uncertain factors. We then utilize real-world data from Pecan Street Inc., which contains the power consumption profile of more than 1; 000 households. In average, the results reveal that we can achieve around 12% reduction on peak-to-average ratio (PAR) and 11% reduction on load variance.
  arXiv  Detail & Related papers  (2020-06-29T15:01:51Z)
• Multi-Agent Meta-Reinforcement Learning for Self-Powered and Sustainable Edge Computing Systems [87.4519172058185]
  An effective energy dispatch mechanism for self-powered wireless networks with edge computing capabilities is studied. A novel multi-agent meta-reinforcement learning (MAMRL) framework is proposed to solve the formulated problem. Experimental results show that the proposed MAMRL model can reduce up to 11% non-renewable energy usage and by 22.4% the energy cost.
  arXiv  Detail & Related papers  (2020-02-20T04:58:07Z)
• NeurOpt: Neural network based optimization for building energy management and climate control [58.06411999767069]
  We propose a data-driven control algorithm based on neural networks to reduce this cost of model identification. We validate our learning and control algorithms on a two-story building with ten independently controlled zones, located in Italy.
  arXiv  Detail & Related papers  (2020-01-22T00:51:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.