A deep bi-directional long-short term memory neural network-based methodology to enhance short-term electricity load forecasting for residential applications

Atef, Sara; Nakata, Keiichi; Eltawil, Amr B.

doi:10.1016/j.cie.2022.108364

Cited by 21 publications

(14 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This article presents a relevant literature systematic review on STLF in the forecasting in the residential sector for electricity demand. The protocol Preferred-Reporting Items for Systematic-Review and Meta-Analysis (PRISMA) was applied due to its ability to increase the value and quality of systematic review compared to other forms of review [11].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Short-Term Load Forecasting of Electricity Demand for the Residential Sector Based on Modelling Techniques: A Systematic Review

Rodrigues¹,

Cardeira²,

Calado³

et al. 2023

Preprint

View full text Add to dashboard Cite

In this paper, a systematic literature review is presented, through a survey in the main digital databases, about modelling methods for Short-Term Load Forecasting (STLF) for hourly electricity demand for residential electricity and to realize the performance evolution and impact of the Artificial Intelligent (AI) in STLF. With these specific objectives, it was developed a conceptual framework on the subject, a systematic review of the literature based on scientific publications with high impact and a bibliometric study directed to the scientific production of AI and STLF. The review of research articles over a 10-year period, which takes place between 2012-2022, uses the Preferred Reporting Items for Systematic and Meta-Analyses (PRISMA) method. This research resulted in more than 300 articles, available in 4 (four) databases: Web of Science, IEEE Xplore, Scopus and Science Direct. The research was organized around 3 (three) central themes, which were defined through keywords: STLF, Electricity, Residential and their corresponding synonyms. 334 research articles were analyzed and identified the year of publication, journal, author, geography by continent and country and the area of application. Of the 334 documents found in the initial research and after applying the inclusion/exclusion criteria, which allowed delimiting the subject addressed in the topics of interest for analysis, 37 (thirty-seven) documents are in English (25 are journal articles and 12 are conference papers). The results point to a diversity of modelling techniques and associated algorithms. The corresponding performance is measured with different metrics and, therefore, cannot be compared directly. Hence, it should be desirable to have a unified data set together with a set of benchmarks with well-defined metrics for a clear comparison of all the modelling techniques and the corresponding algorithms.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Those that are data-driven, are usually applied with artificial intelligence techniques -equal to extrapolation techniques -and engineering methodsequal to correlation techniques. Even so, no single method is scientifically accepted as being better than others in all situations [11].…”

Section: Introductionmentioning

confidence: 99%

Short-Term Load Forecasting of Electricity Demand for the Residential Sector Based on Modelling Techniques: A Systematic Review

Rodrigues¹,

Cardeira²,

Calado³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The research in this paper centers on the problem of power load forecasting and data security protection based on federated learning. Common power load forecasting techniques include time series analysis [4], regression analysis [5], neural networks [6] , and generative adversarial networks [7]. In addition, as an important development in the field of machine learning, the time series transformer has shown high potential in processing time series data, as well as a strong migration learning capability [8], providing a promising alternative to traditional neural networks [9].…”

Section: Literature Reviewmentioning

confidence: 99%

An IHPO-WNN-Based Federated Learning System for Area-Wide Power Load Forecasting Considering Data Security Protection

Shi,

Zhou,

et al. 2023

Energies

View full text Add to dashboard Cite

With the rapid growth of power demand and the advancement of new power system intelligence, smart energy measurement system data quality and security are also facing the influence of diversified factors. To solve the series of problems such as low data prediction efficiency, poor security perception, and “data islands” of the new power system, this paper proposes a federated learning system based on the Improved Hunter–Prey Optimizer Optimized Wavelet Neural Network (IHPO-WNN) for the whole-domain power load prediction. An improved HPO algorithm based on Sine chaotic mapping, dynamic boundaries, and a parallel search mechanism is first proposed to improve the prediction and generalization ability of wavelet neural network models. Further considering the data privacy in each station area and the potential threat of cyber-attacks, a localized differential privacy-based federated learning architecture for load prediction is designed by using the above IHPO-WNN as a base model. In this paper, the actual dataset of a smart energy measurement master station is selected, and simulation experiments are carried out through MATLAB software to test and examine the performance of IHPO-WNN and the federal learning system, respectively, and the results show that the method proposed in this paper has high prediction accuracy and excellent practical performance.

show abstract

“…If the MSE is 0.00, it indicates that the prediction model contains no error values [24]. The absolute mean value of the percentage error between the actual and predicted values is calculated using MAPE [25].…”

Section: 𝑦 = 𝑓(𝑥 − 𝑡)mentioning

confidence: 99%

Day Ahead Energy Consumption Forecasting Through Time-Series Neural Network

Chitra²

2023

IJEEI

View full text Add to dashboard Cite

Demand response management through appliance scheduling can effectively decrease electricity bills. Similarly, it can decrease the peak demand of both consumers and the utility grid. However, prior knowledge of the load profile of the consumer is required for effective appliance scheduling. This work developed a novel time-series forecasting model within the shallow neural network framework to predict the load curve for optimal planning of demand response by a nonlinear autoregressive network with exogenous input network. The models were tested on a dataset including 744 samples obtained at one-hour intervals using a smart meter. The algorithms such as Levenberg-Marquard, scaled conjugate gradient, and Bayesian regularisation were applied to train the model. In particular, finding the optimal combination of the training algorithm, the hidden number of neurons, and the delay parameter was of importance. The results were compared with conventional seasonal autoregressive integrated moving average statistical model and a long shortterm memory network. The results indicated that the optimum methodology is a nonlinear autoregressive network with exogenous inputs using the Bayesian regularisation algorithm, which has the lowest MSE value in the training and testing phases of 0.0031 and 0.0029, respectively. It is practical to continue designing artificial neural networks to analyse hourly load consumption in the context of the positive outcomes acquired.

show abstract

A deep bi-directional long-short term memory neural network-based methodology to enhance short-term electricity load forecasting for residential applications

Cited by 21 publications

References 32 publications

Short-Term Load Forecasting of Electricity Demand for the Residential Sector Based on Modelling Techniques: A Systematic Review

Short-Term Load Forecasting of Electricity Demand for the Residential Sector Based on Modelling Techniques: A Systematic Review

An IHPO-WNN-Based Federated Learning System for Area-Wide Power Load Forecasting Considering Data Security Protection

Day Ahead Energy Consumption Forecasting Through Time-Series Neural Network

Contact Info

Product

Resources

About