Neural network model with Monte Carlo algorithm for electricity demand forecasting in Queensland

Yong, Binbin; Xu, Zijian; Shen, Jun; Chen, Huaming; Tian, Yanshan; Zhou, Qing

doi:10.1145/3014812.3014861

Cited by 22 publications

(11 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the method descripted above, the BP model needs to standardize the data before the operation. After that, a one-layer BP network was built [30]. The one-layer network includes an input layer, a hidden layer, and an output layer.…”

Section: The Application Of Back-propagation Network Model (Bp) In Fomentioning

confidence: 99%

“…Few studies use multiple combined methods to predict the research object at the same time. For example, in the application of the grey model, Chen et al [30] proposed two grey interval prediction methods: the interval grey model (abbreviated as: GM (1,1)) and the interval nonlinear grey Bernoulli model (NGBM (1,1)) for the problem of estimation range, which respectively predict minority and uncertain time series data. Yuan et al [31] also used the GM (1,1) model and the Autoregressive Integrated Moving Average model (ARIMA) to predict the total energy consumption in China.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Forecasting Coal Consumption in India by 2030: Using Linear Modified Linear (MGM-ARIMA) and Linear Modified Nonlinear (BP-ARIMA) Combined Models

Yang

2019

Sustainability

View full text Add to dashboard Cite

India's coal consumption is closely related to greenhouse gas emissions and the balance of supply and demand in energy trading markets. Most existing research on India focuses on total energy, renewable energy and energy intensity. To fill this gap, this study used two single forecasting models: the metabolic grey model (MGM) and the Back-Pro-Pagation Network (BP) to make predictions. In addition, based on these two single models, this study also developed the ARIMA correction principle and derived two combined models: the metabolic grey model, the Autoregressive Integrated Moving Average model (MGM-ARIMA) and Back-Pro-Pagation Network; and the Autoregressive Integrated Moving Average model (BP-ARIMA). After fitting India's coal consumption during 1995-2017, the average relative errors of the four models were 2.28%, 1.53%, 1.50% and 1.42% respectively. The forecast results show that coal consumption in India will continue to increase at an average annual rate of 2.5% during the period from 2018-2030.

show abstract

Section: The Application Of Back-propagation Network Model (Bp) In Fomentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Forecasting Coal Consumption in India by 2030: Using Linear Modified Linear (MGM-ARIMA) and Linear Modified Nonlinear (BP-ARIMA) Combined Models

Yang

2019

Sustainability

View full text Add to dashboard Cite

show abstract

“…2, GVM is a new type of learning machine based on 3-layer ANN, which is thought effective in finding relationship between training data [6]. Since proposed by Zhao [7] in 2016, GVM is proved to be effective for training models with small dataset [8,9,10,11], which is suitable for our system to forecast simulation time when there is lack of training dataset. Instead of traditional back propagation (BP) algorithm [12], a GVM model is trained by Monte Carlo algorithm (MC), which endures GVM the ability to freely train itself with the increase of the training dataset collected by our system.…”

Section: Web Applicationmentioning

confidence: 99%

GVM based intuitive simulation web application for collision detection

Yong

Shen

et al. 2018

Neurocomputing

Self Cite

View full text Add to dashboard Cite

Computer simulation, which has been proved to be an effective approach to problem solving, is nowadays widely used in modern science. However, it requires a lot of computing resources, which are difficult for general users to acquire. In this paper, we design a Web based system to implement on-line simulation system for ordinary users. As a useful example, the simulation of one type of collision detection model is presented in this paper. Moreover, the software application of simulation is offered as a service on Web. Meanwhile, the incorporation of general vector machine (GVM, a type of neural network) to intelligently predict the relationship between simulation parameters and computation resources is presented, which could further provide more information for system monitoring and scheduling. The system has demonstrated efficiency and intuitiveness for users of this type of applications. AbstractComputer simulation, which has been proved to be an effective approach to problem solving, is nowadays widely used in modern science. However, it requires a lot of computing resources, which are difficult for general users to acquire. In this paper, we design a Web based system to implement on-line simulation system for ordinary users. As a useful example, the simulation of one type of collision detection model is presented in this paper. Moreover, the software application of simulation is offered as a service on Web. Meanwhile, the incorporation of general vector machine (GVM, a type of neural network) to intelligently predict the relationship between simulation parameters and computation resources is presented, which could further provide more information for system monitoring and scheduling. The system has demonstrated efficiency and intuitiveness for users of this type of applications.

show abstract

“…In 2016, Zhao researched a type of neural network [19], which has a basic structure of a three-layer neural network. Meanwhile, as a mixer of neural network and SVM, the neural network is optimized by Monte Carlo algorithm (MC), and it has been successfully applied in small samples forecasts [16,17]. In this paper, the MC optimized neural network (MCNN) is applied into electricity load forecast, and we further study the deep MCNNs with more than one hidden layer.…”

Section: Introductionmentioning

confidence: 99%

A research of Monte Carlo optimized neural network for electricity load forecast

Yong

Huang

et al. 2019

J Supercomput

Self Cite

View full text Add to dashboard Cite

In this paper, we apply the Monte Carlo Neural Network (MCNN), a type of neural network optimized by Monte Carlo algorithm, to electricity load forecast. Meanwhile, deep MCNNs with one, two and three hidden layers are designed. Results have demonstrated that 3-layers MCNN improves 70.35% accuracy for 7 weeks electricity load forecast, compared with traditional neural network. And 5-layers MCNN improves 17.24% accuracy for 7 weeks forecast. This proves that MCNN has great potential in electricity load forecast. Keywords Monte Carlo • neural network • electricity load forecast • deep MCNNs

show abstract

Neural network model with Monte Carlo algorithm for electricity demand forecasting in Queensland

Cited by 22 publications

References 38 publications

Forecasting Coal Consumption in India by 2030: Using Linear Modified Linear (MGM-ARIMA) and Linear Modified Nonlinear (BP-ARIMA) Combined Models

Forecasting Coal Consumption in India by 2030: Using Linear Modified Linear (MGM-ARIMA) and Linear Modified Nonlinear (BP-ARIMA) Combined Models

GVM based intuitive simulation web application for collision detection

A research of Monte Carlo optimized neural network for electricity load forecast

Contact Info

Product

Resources

About