Decoupling Weather Influence from User Habits for an Optimal Electric Load Forecast System

Massidda, Luca; Marrocu, Marino

doi:10.3390/en10122171

Cited by 13 publications

(8 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the partial least squares, principal component analysis was mainly used to extract components. In addition, through the introduction of the auto-encoder to replace the principal component analysis part of partial least squares, the nonlinear structure in the feature space could be better reflected [ 27 ]. Since the eigenvalue and eigenvector parts could be solved by using a singular value matrix, there was only time complexity when seeking the covariance matrix.…”

Section: Methodsmentioning

confidence: 99%

The Tapio Decoupling Principle and Key Strategies for Changing Factors of Chinese Urban Carbon Footprint Based on Cloud Computing

Shang

Luo

2021

IJERPH

152

View full text Add to dashboard Cite

The expansion of Xi’an City has caused the consumption of energy and land resources, leading to serious environmental pollution problems. For this purpose, this study was carried out to measure the carbon carrying capacity, net carbon footprint and net carbon footprint pressure index of Xi’an City, and to characterize the carbon sequestration capacity of Xi’an ecosystem, thereby laying a foundation for developing comprehensive and reasonable low-carbon development measures. This study expects to provide a reference for China to develop a low-carbon economy through Tapio decoupling principle. The decoupling relationship between CO2 and driving factors was explored through Tapio decoupling model. The time-series data was used to calculate the carbon footprint. The auto-encoder in deep learning technology was combined with the parallel algorithm in cloud computing. A general multilayer perceptron neural network realized by a parallel BP learning algorithm was proposed based on Map-Reduce on a cloud computing cluster. A partial least squares (PLS) regression model was constructed to analyze driving factors. The results show that in terms of city size, the variable importance in projection (VIP) output of the urbanization rate has a strong inhibitory effect on carbon footprint growth, and the VIP value of permanent population ranks the last; in terms of economic development, the impact of fixed asset investment and added value of the secondary industry on carbon footprint ranks third and fourth. As a result, the marginal effect of carbon footprint is greater than that of economic growth after economic growth reaches a certain stage, revealing that the driving forces and mechanisms can promote the growth of urban space.

show abstract

Section: Methodsmentioning

confidence: 99%

The Tapio Decoupling Principle and Key Strategies for Changing Factors of Chinese Urban Carbon Footprint Based on Cloud Computing

Shang

Luo

2021

IJERPH

152

View full text Add to dashboard Cite

show abstract

“…Both types of buildings were equipped with solar PVs, as well as one or several of the following energy storage technologies: lithium-ion batteries, hybrid energy storage systems (HESS) consisting of lithium-ion batteries and capacitors, second-life EV batteries (2LEV), thermal energy storages (TES), and fuel cells (FC) combined with pressurised (H2SS) or metal hydride (MeH2SS) hydrogen storages. The use cases developed and demonstrated an Energy Management Platform [32] and an Energy Forecasting System (EFS) [33][34][35], as well as several other services, enabling market participation of DER and distributed storages through the VPP aggregation concept. This made possible, for example, the provision of FFR by the aggregated batteries [36].…”

Section: Netfficient (2015-2018)mentioning

confidence: 99%

Multi-Energy System Demonstration Pilots on Geographical Islands: An Overview across Europe

Gabderakhmanova

Marinelli

2022

Energies

View full text Add to dashboard Cite

Smart integration of different energy sectors on islands could serve as a key to achieve their energy independence and carbon neutrality goals and facilitate the large-scale penetration of renewables. Demonstration projects play a vital role in testing innovative sector-coupling solutions and exploring their synergies in the real-life environment. They also help to build the required market confidence and awareness, verify and enhance the societal acceptance, and identify and prevent unnecessary risks and complications. The aim of this paper is to provide the reader with a comprehensive review of 19 research projects, which concern the demonstration of sector-coupling technologies on European islands. The projects are funded by the European Commission and started between 2010 and 2020. The review focuses on the exploration of various technical aspects of 28 demo pilots. In addition, it addresses objectives, contributions, and novelty of the demonstrations and analyses barriers, challenges, risks, and success factors reported by project stakeholders. The paper intends to support the decision-makers on the identification, adoption, and replication of successful technologies. Moreover, it provides researchers and other interested parties with lessons learnt to ensure the successful project execution and technology demonstration in future projects.

show abstract

“…SVR is a modified version of the SVM devised by Müller et al [37] to address the time series forecasting problem. It has gained increasing attention over the past decades, especially in electricity demand forecasting [38]. The main objective of SVR is to find a hyperplane function that can recognize patterns in the given time series data.…”

Section: Support Vector Regressionmentioning

confidence: 99%

A Deep Learning Approach to Forecasting Monthly Demand for Residential–Sector Electricity

Son

Kim

2020

Sustainability

View full text Add to dashboard Cite

Forecasting electricity demand at the regional or national level is a key procedural element of power-system planning. However, achieving such objectives in the residential sector, the primary driver of peak demand, is challenging given this sector’s pattern of constantly fluctuating and gradually increasing energy usage. Although deep learning algorithms have recently yielded promising results in various time series analyses, their potential applicability to forecasting monthly residential electricity demand has yet to be fully explored. As such, this study proposed a forecasting model with social and weather-related variables by introducing long short-term memory (LSTM), which has been known to be powerful among deep learning-based approaches for time series forecasting. The validation of the proposed model was performed using a set of data spanning 22 years in South Korea. The resulting forecasting performance was evaluated on the basis of six performance measures. Further, this model’s performance was subjected to a comparison with the performance of four benchmark models. The performance of the proposed model was exceptional according to all of the measures employed. This model can facilitate improved decision-making regarding power-system planning by accurately forecasting the electricity demands of the residential sector, thereby contributing to the efficient production and use of resources.

show abstract

Decoupling Weather Influence from User Habits for an Optimal Electric Load Forecast System

Cited by 13 publications

References 44 publications

The Tapio Decoupling Principle and Key Strategies for Changing Factors of Chinese Urban Carbon Footprint Based on Cloud Computing

The Tapio Decoupling Principle and Key Strategies for Changing Factors of Chinese Urban Carbon Footprint Based on Cloud Computing

Multi-Energy System Demonstration Pilots on Geographical Islands: An Overview across Europe

A Deep Learning Approach to Forecasting Monthly Demand for Residential–Sector Electricity

Contact Info

Product

Resources

About