Feature Analysis of Generalized Load Patterns Considering Active Load Response to Real-Time Pricing

Li, Jinghua; Lei, Yongsheng; Huang, Qian; Qin, Zhijun; Chen, Bo

doi:10.1109/access.2019.2936497

Cited by 7 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…and behavioral data is available, instead of just using the total household consumption collected by the smart meter. One exception is [24], which describes a methodology based on an elasticity coefficient (approximated by a Gaussian distribution) to estimate indices that characterize the impact of real-time prices in the consumption pattern, such as proportion of maximum load decrease, proportion of peak-valley difference of load decrease, etc. The method consisted in an empirical rule-based calculation of transferred consumption between periods, which was only applied to aggregated consumption of an electric power system and not to households.…”

Section: B Data Generation Methodsmentioning

confidence: 99%

“…Moreover, in comparison to [24], the proposed method is non-parametric and estimates changes in consumption profiles by applying a deep learning model without empirical assumptions about load shifting, showing a high capacity to learn behavioral changes when consumers experience different tariff schemes. In statistical literacy, the proposed method corresponds to sampling random vectors from a given joint density function, which was also explored in the renewable energy forecasting literature to generate temporal trajectories from conditional marginal probability distributions (see [25] and [26] for wind energy trajectories forecast with Gaussian copula and generalized adversarial networks correspondingly).…”

Section: Contributionsmentioning

confidence: 99%

See 1 more Smart Citation

Simulating Tariff Impact in Electrical Energy Consumption Profiles With Conditional Variational Autoencoders

Brégère

Bessa

2020

IEEE Access

View full text Add to dashboard Cite

The implementation of efficient demand response (DR) programs for household electricity consumption would benefit from data-driven methods capable of simulating the impact of different tariffs schemes. This paper proposes a novel method based on conditional variational autoencoders (CVAE) to generate, from an electricity tariff profile combined with weather and calendar variables, daily consumption profiles of consumers segmented in different clusters. First, a large set of consumers is gathered into clusters according to their consumption behavior and price-responsiveness. The clustering method is based on a causality model that measures the effect of a specific tariff on the consumption level. Then, daily electrical energy consumption profiles are generated for each cluster with CVAE. This non-parametric approach is compared to a semi-parametric data generator based on generalized additive models. Experiments in a publicly available data set show that, the proposed method presents comparable performance to the semiparametric one when it comes to generating the average value of the original data (13% difference in root mean square error). The main contribution from this new method is the capacity to reproduce rebound and side effects in the generated consumption profiles. Indeed, the application of a special electricity tariff over a time window may also affect consumption outside this time window. Another contribution is that the proposed clustering approach is capturing the reaction to a tariff change. When compared to a clustering method with classical features (min, max and average consumption), the improvement in the Calinski-Harabasz index was 128% for consumers associated with tariff changes.

show abstract

Section: B Data Generation Methodsmentioning

confidence: 99%

Section: Contributionsmentioning

confidence: 99%

Simulating Tariff Impact in Electrical Energy Consumption Profiles With Conditional Variational Autoencoders

Brégère

Bessa

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…and behavioral data is available, instead of just using the total household consumption collected by the smart meter. One exception is Li et al [2019], which describes a methodology based on an elasticity coefficient (approximated by a Gaussian distribution) to estimate indices that characterize the impact of real-time prices in the consumption pattern, such as proportion of maximum load decrease, proportion of peak-valley difference of load decrease, etc. The method consisted in an empirical rule-based calculation of transferred consumption between periods, which was only applied to aggregated consumption of an electric power system and not to households.…”

Section: Data Generation Methodsmentioning

confidence: 99%

“…Moreover, in comparison to Li et al [2019], the proposed method is non-parametric and estimates changes in consumption profiles by applying a deep learning model without empirical assumptions about load shifting, showing a high capacity to learn behavioral changes when consumers experience different tariff schemes. In statistical literacy, the proposed method corresponds to sampling random vectors from a given joint density function, which was also explored in the renewable energy forecasting literature to generate temporal trajectories from conditional marginal probability distributions (see Pinson et al [2009] and Chen et al [2018] for wind energy trajectories forecast with Gaussian copula and generalized adversarial networks correspondingly).…”

Section: Contributionsmentioning

confidence: 99%

Simulating Tariff Impact in Electrical Energy Consumption Profiles with Conditional Variational Autoencoders

Brégère¹,

Bessa²

2020

Preprint

View full text Add to dashboard Cite

The implementation of efficient demand response (DR) programs for household electricity consumption would benefit from data-driven methods capable of simulating the impact of different tariffs schemes. This paper proposes a novel method based on conditional variational autoencoders (CVAE) to generate, from an electricity tariff profile combined with exogenous weather and calendar variables, daily consumption profiles of consumers segmented in different clusters. First, a large set of consumers is gathered into clusters according to their consumption behavior and price-responsiveness. The clustering method is based on a causality model that measures the effect of a specific tariff on the consumption level. Then, daily electrical energy consumption profiles are generated for each cluster with CVAE. This non-parametric approach is compared to a semi-parametric data generator based on generalized additive models and that uses prior knowledge of energy consumption. Experiments in a publicly available data set show that, the proposed method presents comparable performance to the semi-parametric one when it comes to generating the average value of the original data. The main contribution from this new method is the capacity to reproduce rebound and side effects in the generated consumption profiles. Indeed, the application of a special electricity tariff over a time window may also affect consumption outside this time window. Another contribution is that the clustering approach segments consumers according to their daily consumption profile and elasticity to tariff changes. These two results combined are very relevant for an ex-ante testing of future DR policies by system operators, retailers and energy regulators.

show abstract

An improved convolutional neural network with load range discretization for probabilistic load forecasting

Huang

Zhu

2020

Energy

View full text Add to dashboard Cite

Feature Analysis of Generalized Load Patterns Considering Active Load Response to Real-Time Pricing

Cited by 7 publications

References 23 publications

Simulating Tariff Impact in Electrical Energy Consumption Profiles With Conditional Variational Autoencoders

Simulating Tariff Impact in Electrical Energy Consumption Profiles With Conditional Variational Autoencoders

Simulating Tariff Impact in Electrical Energy Consumption Profiles with Conditional Variational Autoencoders

An improved convolutional neural network with load range discretization for probabilistic load forecasting

Contact Info

Product

Resources

About