Assessing the performance of deep learning models for multivariate probabilistic energy forecasting

Mashlakov, Aleksei; Kuronen, Toni; Lensu, Lasse; Kaarna, Arto; Honkapuro, Samuli

doi:10.1016/j.apenergy.2020.116405

Cited by 57 publications

(22 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, renewable energies can reduce price volatility in Hydrothermal power markets (70) . Thus, the bibliometric analysis showed that approximately 60% of the papers of the last five years had the price forecast as the main objective (29,66,(71)(72)(73)(74) . In this way, price prediction has become a principal method for planning and operations in energy systems.…”

Section: Historical Factorsmentioning

confidence: 99%

Determinantes del Precio de la Electricidad en Mercados No Regulados: Un Análisis Bibliométrico

Gómez

Londoño-Hernández

Manotas-Duque

2021

inycomp

View full text Add to dashboard Cite

Los procesos de liberalización de los mercados eléctricos en diferentes países generaron una nueva forma de definir los precios de la electricidad, lo que ha aumentado la dificultad para modelar y analizar su dinámica. Este estudio presenta un análisis bibliométrico de los determinantes del precio de la electricidad en mercados no regulados. La investigación sistemática a través de la base de datos Scopus, para el período enero de 1979 - abril de 2021, permitió observar 636 documentos indexados. Los resultados mostraron un aumento en el número de documentos por año en las últimas dos décadas. Además, los países con mayor producción fueron China, Estados Unidos y Alemania según su número de publicaciones. Sin embargo, Estados Unidos, Canadá e Irán tuvieron el mayor impacto según la relación entre el número de documentos y el número de citas. Los principales determinantes fueron las condiciones económicas y de mercado, el clima, el funcionamiento del sistema eléctrico y la demanda de los clientes. Del mismo modo, la tendencia de investigación en los últimos años se enfoca en pronosticar el precio con mayor eficiencia.

show abstract

Section: Historical Factorsmentioning

confidence: 99%

Determinantes del Precio de la Electricidad en Mercados No Regulados: Un Análisis Bibliométrico

Gómez

Londoño-Hernández

Manotas-Duque

2021

inycomp

View full text Add to dashboard Cite

show abstract

“…a. Prediction Interval Coverage Probability (PICP): assessing the accuracy of the predictive interval, defined as the percentage of time the actual PV power stays within the predictive confidence interval; see [23]. The 90%-PICP is used.…”

Section: Performance Metrics For Time-series Forecastmentioning

confidence: 99%

“…On the other hand, extensive researches have been made on weather-dependent scenario generation [21], [22] and forecast [23], [24], providing trajectories and statistical information like interval and distribution. Especially, the latest deep learning (DL)-based time-series forecasts capture the non-uniform patterns of PV power [19], [25]- [27].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Achieving an Accurate Random Process Model for PV Power using Cheap Data: Leveraging the SDE and Public Weather Reports

Qiu

Lin

Zhou

et al. 2021

Preprint

View full text Add to dashboard Cite

The stochastic differential equation (SDE)-based random process models of volatile renewable energy sources (RESs) jointly capture the evolving probability distribution and temporal correlation in continuous time. It has enabled recent studies to remarkably improve the performance of power system dynamic uncertainty quantification and optimization. However, considering the non-homogeneous random process nature of PV, there still remains a challenging question: how can a realistic and accurate SDE model for PV power be obtained that reflects its weatherdependent uncertainty in online operation, especially when highresolution numerical weather prediction (NWP) is unavailable for many distributed plants? To fill this gap, this article finds that an accurate SDE model for PV power can be constructed by only using the cheap data from low-resolution public weather reports. Specifically, an hourly parameterized Jacobi diffusion process is constructed to recreate the temporal patterns of PV volatility during a day. Its parameters are mapped from the public weather report using an ensemble of extreme learning machines (ELMs) to reflect the varying weather conditions. The SDE model jointly captures intraday and intrahour volatility. Statistical examination based on real-world data collected in Macau shows the proposed approach outperforms a selection of state-of-the-art deep learningbased time-series forecast methods.

show abstract

“…These actions are medium-to-long term energy strategies, whose energy saving calculation are based on forecasting energy models, whose effectiveness can significantly affect the energy scenarios. Statistical models are the most common tools adopted for this kind of analysis; however, regression analysis, fuzzy systems, and Artificial Neural Networks (ANN) are also interesting tools proposed in the Literature [2][3][4][5][6][7]. In particular, ANNs are applied in different fields with several purposes [8]: for electricity consumption forecasting of buildings [6,7] or for building energy evaluation in agreement with national regulations [9,10].…”

Section: Introductionmentioning

confidence: 99%

Tool for supporting local energy strategies: forecasting energy plans with Artificial Neural Network in Umbria Region

Palladino

Nardi

2021

E3S Web Conf.

View full text Add to dashboard Cite

In order to reduce the greenhouse gas emission and to improve the energy efficiency of buildings, European Member States have to plan medium-to-long term strategies as reliable as possible. In this context, the present work aims to discuss the potentiality of Artificial Neural Network (ANN) as a support tool for medium-to-long term forecasting analysis of energy efficiency strategies in Umbria Region (central Italy) chosen as case study. Parametric energy simulations of several archetypes buildings were carried out in compliance with the current Italian regulations by changing the form, thermal properties, boundary conditions, and technical building systems. An ANN able to forecast primary energy need was trained to forecast the energy need of building-stock of Umbria Region and to evaluate the effectiveness of several potential energy actions (such as thermal coat or technical building systems replacement) over the years. Results confirm the potential of use of ANN as a support tool in energy forecasting analysis for local Authorities. ANN is capable of forecasting different future scenarios allowing correctly planning energy actions to be implemented as well as their priority. The results open to several scenarios of interest, such as the application of the same approach at national level.

show abstract

Assessing the performance of deep learning models for multivariate probabilistic energy forecasting

Cited by 57 publications

References 36 publications

Determinantes del Precio de la Electricidad en Mercados No Regulados: Un Análisis Bibliométrico

Determinantes del Precio de la Electricidad en Mercados No Regulados: Un Análisis Bibliométrico

Achieving an Accurate Random Process Model for PV Power using Cheap Data: Leveraging the SDE and Public Weather Reports

Tool for supporting local energy strategies: forecasting energy plans with Artificial Neural Network in Umbria Region

Contact Info

Product

Resources

About