Prediction of Energy Consumption for Variable Customer Portfolios Including Aleatoric Uncertainty Estimation (2021-10-01T00:00:00.000000Z)

TL;DR

A method to calculate hourly day-ahead energy consumption forecasts which include an estimation of the aleatoric uncertainty is proposed and it is demonstrated how these random variables corresponding to single customers can be aggregated to probabilistic forecasts of customer portfolios of arbitrary composition.

Abstract

Using hourly energy consumption data recorded by smart meters, retailers can estimate the day-ahead energy consumption of their customer portfolio. Deep neural networks are especially suited for this task as a huge amount of historical consumption data is available from smart meter recordings to be used for model training. Probabilistic layers further enable the estimation of the uncertainty of the consumption forecasts. Here, we propose a method to calculate hourly day-ahead energy consumption forecasts which include an estimation of the aleatoric uncertainty. To consider the statistical properties of energy consumption values, the aleatoric uncertainty is modeled using lognormal distributions whose parameters are calculated by deep neural networks. As a result, predictions of the hourly day-ahead energy consumption of single customers are represented by random variables drawn from lognormal distributions obtained as output from the neural network. We further demonstrate, how these random variables corresponding to single customers can be aggregated to probabilistic forecasts of customer portfolios of arbitrary composition.

Authors

Oliver Mey

2 papers

André Schneider

2 papers

Olaf Enge-Rosenblatt

2 papers

Prediction of Energy Consumption for Variable Customer Portfolios Including Aleatoric Uncertainty Estimation

TL;DR

Abstract

Authors

References25 items

Accurate Prediction of Hourly Energy Consumption in a Residential Building Based on the Occupancy Rate Using Machine Learning Approaches

Using Bayesian Deep Learning to Capture Uncertainty for Residential Net Load Forecasting

Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods

Probabilistic individual load forecasting using pinball loss guided LSTM

Deep Learning for Household Load Forecasting—A Novel Pooling Deep RNN

Short-Term Load Forecasting With Deep Residual Networks

Combining Probabilistic Load Forecasts

Predictive modeling for US commercial building energy use: A comparison of existing statistical and machine learning algorithms using CBECS microdata

Review of Smart Meter Data Analytics: Applications, Methodologies, and Challenges

Machine learning approaches for estimating commercial building energy consumption

TensorFlow Distributions

Building Energy Consumption Prediction: An Extreme Deep Learning Approach

Deep learning for estimating building energy consumption

Forecasting Uncertainty in Electricity Smart Meter Data by Boosting Additive Quantile Regression

Practical lognormal framework for household energy consumption modeling

Characterizing probability density distributions for household electricity load profiles from high-resolution electricity use data

Smart Meters in Smart Grid: An Overview

Probabilistic characterisation of the aggregated residential load patterns

Energy Consumption Curves of 499 Customers from Spain

A Novel CNN-GRU-Based Hybrid Approach for Short-Term Residential Load Forecasting

Review on probabilistic forecasting of photovoltaic power production and electricity consumption

A review of data-driven building energy consumption prediction studies

Recent advances in electricity price forecasting: A review of probabilistic forecasting

Probabilistic electric load forecasting

Source code of this work

Field of Study

Journal Information

Name

Page