Day-ahead load forecasting using improved grey Verhulst model

Mbae, Ariel Mutegi; Nwulu, Nnamdi

doi:10.1108/jedt-12-2019-0337

Cited by 5 publications

(4 citation statements)

References 35 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Long short-term memory (LSTM) developed from a recurrent neural network (RNN) can deal with long-term dependencies of time series, avoiding gradient vanishing and exploding of the RNN [17]. A convolutional neural network (CNN) can effectively capture the local relationships among adjacent time points [18] and is also widely used in many fields, such as image recognition [19], renewable energy forecasting [20], as well as load forecasting [21]. However, a large number of hyperparameters of CNN can easily result in overfitting of the training model.…”

Section: Introductionmentioning

confidence: 99%

Short-Term Load Forecasting Based on VMD and Deep TCN-Based Hybrid Model with Self-Attention Mechanism

Xiong,

Liu,

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Due to difficulties with electric energy storage, balancing the supply and demand of the power grid is crucial for the stable operation of power systems. Short-term load forecasting can provide an early warning of excessive power consumption for utilities by formulating the generation, transmission and distribution of electric energy in advance. However, the nonlinear patterns and dynamics of load data still make accurate load forecasting a challenging task. To address this issue, a deep temporal convolutional network (TCN)-based hybrid model combined with variational mode decomposition (VMD) and self-attention mechanism (SAM) is proposed in this study. Firstly, VMD is used to decompose the original load data into a series of intrinsic mode components that are used to reconstruct a feature matrix combined with other external factors. Secondly, a three-layer convolutional neural network is used as a deep network to extract in-depth features between adjacent time points from the feature matrix, and then the output matrix captures the long-term temporal dependencies using the TCN. Thirdly, long short-term memory (LSTM) is utilized to enhance the extraction of temporal features, and the correlation weights of spatiotemporal features are future-adjusted dynamically using SAM to retain important features during the model training. Finally, the load forecasting results can be obtained from the fully connected layer. The effectiveness and generalization of the proposed model were validated on two real-world public datasets, ISO-NE and GEFCom2012. Experimental results indicate that the proposed model significantly improves the prediction accuracy in terms of evaluation metrics, compared with other contrast models.

show abstract

Section: Introductionmentioning

confidence: 99%

Short-Term Load Forecasting Based on VMD and Deep TCN-Based Hybrid Model with Self-Attention Mechanism

Xiong,

Liu,

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…By considering the risk factors affecting renewable energy (Addy et al , 2019), a total of 175 GW of solar power will be required up to the year 2022 in India. This huge amount of power cannot be generated from conventional thermal power plants as these sources are at their edge of depletion and electrical energy prediction (Mhundwa and Simon, 2021) as well as load forecasting (Mbae and Nwulu, 2020) are critical to investigate. Thus, other clean sources of energy are required to be used to counter balance the highly releasing CO 2 in the atmosphere (Razykov et al , 2011).…”

Section: Introductionmentioning

confidence: 99%

A new solar powered robotic arm guided master–slave electric motors of biomass conveyor

Ghodki

2022

JEDT

View full text Add to dashboard Cite

Purpose Electric motor heating during biomass recovery and its handling on conveyor is a serious concern for the motor performance. Thus, the purpose of this paper is to design and develop a hardware prototype of master–slave electric motors based biomass conveyor system to use the motors under normal operating conditions without overheating. Design/methodology/approach The hardware prototype of the system used master–slave electric motors for embedded controller operated robotic arm to automatically replace conveyor motors by one another. A mixed signal based embedded controller (C8051F226DK), fully compliant with IEEE 1149.1 specifications, was used to operate the entire system. A precise temperature measurement of motor with the help of negative temperature coefficient sensor was possible due to the utilization of industry standard temperature controller (N76E003AT20). Also, a pulse width modulation based speed control was achieved for master–slave motors of biomass conveyor. Findings As compared to conventional energy based mains supply, the system is self-sufficient to extract more energy from solar supply with an energy increase of 11.38%. With respect to conventional energy based \ of 47.31%, solar energy based higher energy saving of 52.69% was reported. Also, the work achieved higher temperature reduction of 34.26% of the motor as compared to previous cooling options. Originality/value The proposed technique is free from air, liquid and phase-changing material based cooling materials. As a consequence, the work prevents the wastage of these materials and does not cause the risk of health hazards. Also, the motors are used with their original dimensions without facing any leakage problems.

show abstract

“…ARIMA involves a stochastic difference equation frequently used to model stochastic disturbances in a time series analysis. As the load-time series analysis is highly complex, simple linear ARIMA-based modeling methods cannot be used for modeling the load curves (Huang and Shih, 2003;Singh et al, 2012;Mbae and Nwulu, 2020). This linear nature of conventional methods made the researchers move toward artificial neural network (ANN)based prediction techniques to capture non-linearity (Singh et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Modeling of a simplified hybrid algorithm for short-term load forecasting in a power system network

Mayilsamy

Akbarali

et al. 2021

COMPEL

View full text Add to dashboard Cite

Purpose The purpose of this paper is to develop a hybrid algorithm, which is a blend of auto-regressive integral moving average (ARIMA) and multilayer perceptron (MLP) for addressing the non-linearity of the load time series. Design/methodology/approach Short-term load forecasting is a complex process as the nature of the load-time series data is highly nonlinear. So, only ARIMA-based load forecasting will not provide accurate results. Hence, ARIMA is combined with MLP, a deep learning approach that models the resultant data from ARIMA and processes them further for Modelling the non-linearity. Findings The proposed hybrid approach detects the residuals of the ARIMA, a linear statistical technique and models these residuals with MLP neural network. As the non-linearity of the load time series is approximated in this error modeling process, the proposed approach produces accurate forecasting results of the hourly loads. Originality/value The effectiveness of the proposed approach is tested in the laboratory with the real load data of a metropolitan city from South India. The performance of the proposed hybrid approach is compared with the conventional methods based on the metrics such as mean absolute percentage error and root mean square error. The comparative results show that the proposed prediction strategy outperforms the other hybrid methods in terms of accuracy.

show abstract

Day-ahead load forecasting using improved grey Verhulst model

Cited by 5 publications

References 35 publications

Short-Term Load Forecasting Based on VMD and Deep TCN-Based Hybrid Model with Self-Attention Mechanism

Short-Term Load Forecasting Based on VMD and Deep TCN-Based Hybrid Model with Self-Attention Mechanism

A new solar powered robotic arm guided master–slave electric motors of biomass conveyor

Modeling of a simplified hybrid algorithm for short-term load forecasting in a power system network

Contact Info

Product

Resources

About