2019
DOI: 10.1016/j.apenergy.2019.113315
|View full text |Cite
|
Sign up to set email alerts
|

A comparison of day-ahead photovoltaic power forecasting models based on deep learning neural network

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
133
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
6
2

Relationship

0
8

Authors

Journals

citations
Cited by 411 publications
(157 citation statements)
references
References 29 publications
0
133
0
Order By: Relevance
“…For example, there are some good examples of forecasting work based on LSTM. Wang et al [53] establish a hybrid day-ahead PV power forecasting model based on CNN and LSTM. This model uses CNN first extracts local features of data and applies LSTM to extracts the overall timing features of data, and the prediction performance is outstanding.…”
Section: Lstm Recurrent Neural Networkmentioning
confidence: 99%
“…For example, there are some good examples of forecasting work based on LSTM. Wang et al [53] establish a hybrid day-ahead PV power forecasting model based on CNN and LSTM. This model uses CNN first extracts local features of data and applies LSTM to extracts the overall timing features of data, and the prediction performance is outstanding.…”
Section: Lstm Recurrent Neural Networkmentioning
confidence: 99%
“…The traditional feedforward neural networks only accept information from input nodes. They do not "remember" input to different time series [31]. Thus, it cannot extract the hidden features which have a long-time dependency from raw data.…”
Section: Lstmmentioning
confidence: 99%
“…Different from other CNNs, we adopted only one pooling layer to reduce the dimension of extracted features due to the data we used with lees dimensions, which is motivated by [31]. Firstly, CNN models the multi-scale local features from raw sample tensor Reshape(x(t)) at three-scale convolution operations-Conv1_1, Conv1_2, and Conv1_3-using different size kernels with shapes of 1 × 2, 1 × 3, 1 × 4.…”
Section: Cnn Feature Extractionmentioning
confidence: 99%
“…Since ants move stochastically when looking for food in nature, a random walk is selected by using Equations (13) and (14).…”
Section: Ant Lion Optimization Algorithmmentioning
confidence: 99%
“…In these equations, cumsum represents the cumulative sum, n represents the maximum number of iterations, t is the step of random walk, r(t) is a stochastic function and rand represents a random number generated with a uniform distribution in the range of [0, 1]. Since each search space has a boundary, Equations (13) and (14) cannot be used directly to update the position of ants. In order to keep the random walk of ants in the search space, normalization is performed at each iteration by using Equation (15).…”
Section: Ant Lion Optimization Algorithmmentioning
confidence: 99%