A Deep Learning Neural Network for the Residential Energy Consumption Prediction

Huang, Jinhai; Pang, Chengxin; Yang, Weijun; Zeng, Xinhua; Zhang, Jun; Huang, Chizhi

doi:10.1002/tee.23543

Cited by 9 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In January 2022, Huang et al [88] proposed a novel NN based on CNN-attention-bidirectional LSTM (BiLSTM) for residential energy consumption prediction. An attention mechanism was applied to assign different weights to the neurons' outputs so as to strengthen the impact of important information.…”

Section: Residential Building Loadmentioning

confidence: 99%

A Survey on Deep Learning for Building Load Forecasting

Patsakos

Vrochidou

Papakostas

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Energy consumption forecasting is essential for efficient resource management related to both economic and environmental benefits. Forecasting can be implemented through statistical analysis of historical data, application of Artificial Intelligence (AI) algorithms, physical models, and more, and focuses on two directions: the required load for a specific area, e.g., a city, and the required load for a building. Building power forecasting is challenging due to the frequent fluctuation of the required electricity and the complexity and alterability of each building’s energy behavior. This paper focuses on the application of Deep Learning (DL) methods to accurately predict building (residential, commercial, or multiple) power consumption, by utilizing the available historical big data. Research findings are compared to state-of-the-art statistical models and AI methods of the literature to comparatively evaluate their efficiency and justify their future application. The aim of this work is to review up-to-date proposed DL approaches, to highlight the current research status, and to point out emerging challenges and future potential directions. Research revealed a higher interest in residential building load forecasting covering 47.5% of the related literature from 2016 up to date, focusing on short-term forecasting horizon in 55% of the referenced papers. The latter was attributed to the lack of available public datasets for experimentation in different building types, since it was found that in the 48.2% of the related literature, the same historical data regarding residential buildings load consumption was used.

show abstract

Section: Residential Building Loadmentioning

confidence: 99%

A Survey on Deep Learning for Building Load Forecasting

Patsakos

Vrochidou

Papakostas

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…CNN, an attention mechanism, and BiLSTM are combined in the proposed method, with CNN initially used to extract the original data's effective features. The extracted segments are then utilized as the input of attention-BiLSTM to predict energy consumption, with the attention mechanism assigning weights to neurons at each timestamp [27]. A deep neural network (DNN) is an artificial neural network (ANN) with more than one hidden layer, in contrast to the traditional ANN topologies.…”

Section: Introductionmentioning

confidence: 99%

A Data-driven Long-Short Term Load Forecasting with LSTM-RNN Networks

Waheed¹,

Xu²

2023

Preprint

View full text Add to dashboard Cite

Operations and planning of power systems significantly rely on accurate load forecasts specifically after the penetration of renewable energy resources. However, temporal relationships in load data are challenging to capture using traditional statistical and machine learning methods. The application of recurrent neural networks, and more specifically long short-term memory (LSTM) networks, to the modeling of sequence data with extensive temporal relationships has yielded promising results. In this paper, we present a model for predicting future loads using a recurrent neural network with long short-term memory.Effective demand response and distributed renewable energy sources can be better integrated with this technology, which is crucial for the smart grid's stability and power demand estimation. However, it is difficult to perform energy prediction with high accuracy because of influencing elements like climate, society, and seasonality. We evaluate the accuracy of the model by using demand data collected from the German utility. The proposed LSTM-RNN model exhibits significantly lower error rates in 1-24 hours and yearly load forecasts than conventional machine learning techniques. In addition, the model is able to make accurate predictions despite receiving inadequate or noisy inputs. Our findings imply that LSTM-RNN could be used in practice for effective load forecasting.

show abstract

“…Large quantities of clean energy with significant characteristics of randomness and fluctuation constantly gets integrated into the power grid, which intensely impacts the reliability of power grid [1][2][3]. As combination of the emerging digital twin technology and power grid scenario, the digital twin power grid can be used to solve the above problem and fulfill clean energy consumption target [4,5].…”

Section: Introductionmentioning

confidence: 99%

Digital Twin Power Grid Oriented Mobile Edge Network Resource Allocation Model

Han,

Chen,

et al. 2023

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

The integration of vast quantities of clean energy causes intense impact on the power grid reliability. Digital Twin can be used to handle the high‐growth data flow generated in the power grid, and thus accelerate its digitalization process to fulfill the clean energy consumption target. As the traditional central cloud network structure can no longer effectively support the operation of digital twin power grid, the mobile edge network can be used as a reasonable substitute. To support the information interaction process of the mobile edge network, considering total profit, time delay and energy consumption, this paper proposes the mobile edge network communication and computing resource joint allocation model. On the basis, the GA‐PSO algorithm is proposed to solve the resource allocation optimization function. The feasibility and effectiveness of the proposed model is verified by the related simulation experiment. © 2023 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC.

show abstract

A Deep Learning Neural Network for the Residential Energy Consumption Prediction

Cited by 9 publications

References 34 publications

A Survey on Deep Learning for Building Load Forecasting

A Survey on Deep Learning for Building Load Forecasting

A Data-driven Long-Short Term Load Forecasting with LSTM-RNN Networks

Digital Twin Power Grid Oriented Mobile Edge Network Resource Allocation Model

Contact Info

Product

Resources

About