A novel approach for harmonic tidal currents constitutions forecasting using hybrid intelligent models based on clustering methodologies

Aly, Hamed H.

doi:10.1016/j.renene.2019.09.107

Cited by 25 publications

(15 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…WNNs have the capacity to capture non-linear correlations between input and output data, as well as manage noisy or missing data. They are also computationally efficient and can be trained using standard back-propagation techniques [158,159].…”

Section: Wavelet Neural Network (Wnn) For Renewable Energy Forecastingmentioning

confidence: 99%

Forecasting Renewable Energy Generation with Machine learning and Deep Learning: Current Advances and Future Prospects

Benti¹,

Chaka²,

Semie³

2023

Preprint

View full text Add to dashboard Cite

This article presents a review of current advances and future prospects in the field of forecasting renewable energy generation using machine learning (ML) and deep learning (DL) techniques. With the increasing penetration of renewable energy sources (RES) into the electricity grid, accurate forecasting of their generation becomes crucial for efficient grid operation and energy management. Traditional forecasting methods have limitations, and thus ML and DL algorithms have gained popularity due to their ability to learn complex relationships from data and provide accurate predictions. This paper reviews the different approaches and models that have been used for renewable energy forecasting and discusses their strengths and limitations. It also highlights the challenges and future research directions in the field, such as dealing with uncertainty and variability in renewable energy generation, data availability, and model interpretability. Finally, this paper emphasizes the importance of developing robust and accurate renewable energy forecasting models to enable the integration of RES into the electricity grid and facilitate the transition towards a sustainable energy future.

show abstract

Section: Wavelet Neural Network (Wnn) For Renewable Energy Forecastingmentioning

confidence: 99%

Forecasting Renewable Energy Generation with Machine learning and Deep Learning: Current Advances and Future Prospects

Benti¹,

Chaka²,

Semie³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The model was tested using a limited version of 𝑘𝑘-order cross-validation methods (Aly, 2020;Pala and Atici, 2019). The data was divided into 𝑘𝑘=10 sections of equal length.…”

Section: Classificationmentioning

confidence: 99%

Some methods for addressing errors in static AIS data records

2022

View full text Add to dashboard Cite

“…State estimations collect measurements through the use of sensors and metering devices for voltage magnitudes, line flows, and power to monitor the operational status of the grid [8]. State estimation also helps to indicate the presence of false data within these measurements [9]. In traditional state estimation such as WLS, the measurement data is collected from various buses to estimate the state of the grid.…”

Section: Introductionmentioning

confidence: 99%

False Data Detection in a Clustered Smart Grid Using Unscented Kalman Filter

2022

View full text Add to dashboard Cite

The smart grid accessibility over the Internet of Things (IoT) is becoming attractive to electrical grid operators as it brings considerable operational and cost efficiencies. However, this in return creates significant cyber security challenges, such as fortification of state estimation data such as state variables against false data injection attacks (FDIAs). In this paper, a clustered partitioning state estimation (CPSE) technique is proposed to detect FDIA by using static state estimation, namely, weighted least square (WLS) method in conjunction with dynamic state estimation using minimum variance unscented Kalman filter (MV-UKF) which improves the accuracy of state estimation. The estimates acquired from the MV-UKF do not deviate like WLS as these are purely based on the previous iteration saved in the transition matrix. The deviation between the corresponding estimations of WLS and MV-UKF are utilised to partition the smart grid into smaller sub-systems to detect FDIA and then identify its location. To validate the proposed detection technique, FIDAs are injected into IEEE 14-bus, IEEE 30-bus, IEEE 118-bus, and IEEE 300-bus distribution feeder using MATPOWER simulation platform. Our results clearly demonstrate that the proposed technique can locate the attack area efficiently compared to other techniques such as chi square.

show abstract

A novel approach for harmonic tidal currents constitutions forecasting using hybrid intelligent models based on clustering methodologies

Cited by 25 publications

References 12 publications

Forecasting Renewable Energy Generation with Machine learning and Deep Learning: Current Advances and Future Prospects

Forecasting Renewable Energy Generation with Machine learning and Deep Learning: Current Advances and Future Prospects

Some methods for addressing errors in static AIS data records

False Data Detection in a Clustered Smart Grid Using Unscented Kalman Filter

Contact Info

Product

Resources

About