ChapterPDF Available

Electricity Load Forecasting for Each Day of Week Using Deep CNN

Authors:

Abstract and Figures

In smart grid, precise and accurate electricity load forecasting is one of the most challenging tasks. It is due to the high volatile, non-stationary and non-linear behavior of electricity load data. In this paper, a Deep Convolution Neural Network (DCNN) model is proposed to forecast the electricity load for each day of the week of Victoria (Australia). To forecast the electricity load for one day of the week, we analyzed the electricity load data consumed on the same day for the previous three months. To show the usefulness of our proposed scheme, comparison is made with the state of the art forecasting models namely recurrent neural network, extreme learning machine, CNN and auto regressive integrated moving average. Results show that the proposed DCNN has the lowest mean absolute percentage error, mean absolute error and root mean square error of 2.1%, 138.771 and 116.417.
Content may be subject to copyright.
Electricity Load Forecasting for Each Day
of Week Using Deep CNN
Sajjad Khan1, Nadeem Javaid1(B
), Annas Chand2,
Abdul Basit Majeed Khan3, Fahad Rashid4, and Imran Uddin Afridi1
1COMSATS University Islamabad, Islamabad 44000, Pakistan
nadeemjavaidqau@gmail.com
2COMSATS University Islamabad, Abbottabad Campus,
Abbottabad 22010, Pakistan
3Abasyin University Islamabad, Islamabad 44000, Pakistan
4Bahria University Islamabad, Islamabad 44000, Pakistan
http://www.njavaid.com
Abstract. In smart grid, precise and accurate electricity load forecast-
ing is one of the most challenging tasks. It is due to the high volatile, non-
stationary and non-linear behavior of electricity load data. In this paper,
a Deep Convolution Neural Network (DCNN) model is proposed to fore-
cast the electricity load for each day of the week of Victoria (Australia).
To forecast the electricity load for one day of the week, we analyzed the
electricity load data consumed on the same day for the previous three
months. To show the usefulness of our proposed scheme, comparison is
made with the state of the art forecasting models namely recurrent neural
network, extreme learning machine, CNN and auto regressive integrated
moving average. Results show that the proposed DCNN has the low-
est mean absolute percentage error, mean absolute error and root mean
square error of 2.1%, 138.771 and 116.417.
Keywords: Smart grid ·For e casting ·Energy management ·
Neural Network ·Deep learning
1 Background
Forecasting the accurate electricity load demand plays a key role in demand
side management. It helps the generation companies to develop a tolerable pro-
duction plan and avoid energy wastage. For electricity load forecasting many
techniques have been used in literature. These prediction techniques are mainly
classified into three main groups, i.e., data driven techniques, classical techniques
and Artificial Intelligence (AI) techniques. Data driven techniques predict the
desired outcomes on the basis of analysing historical data. Classical techniques
comprises of the statistical and mathematical methods like Autoregressive Inte-
grated Moving Average (ARIMA), Seasonal ARIMA and random forest etc.
c
Springer Nature Switzerland AG 2019
L. Barolli et al. (Eds.): WAINA 2019, AISC 927, pp. 1107–1119, 2019.
https://doi.org/10.1007/978-3-030-15035-8_107
1108 S. Khan et al.
Such methods are effective for one step forecast. AI methods inhibit the behavior
of biological neurons e.g., Feed Forward Neural Network (FFNN), Convolution
Neural Network (CNN) and Long Short Term Memory (LSTM) etc.
In [2], Bayesian network and Multi Layer Perceptron (MLP) are used for
short and long term load forecasting. Bayesian network performs behavioral
analytics using the data obtained from the smart meters. Number of experi-
ments were performed on the obtained data. For Short Term Load Forecasting
(STLF), multiple linear regression is used in [3]. However, it has the limitation
that it can not be used for long term prediction. The authors in [4] performed
electricity load forecasting on the basis of weather data obtained from the mete-
orological department. In this work, load prediction is performed using residual
Neural Network (NN). A framework of different models is used for prediction
in [5]. This framework consists of Gated Recurrent Unit (GRU), Recurrent Neu-
ral Network (RNN) and LSTM. GRU is a variant of the RNN. It outperformed
LSTM and many other statistical models in terms of prediction accuracy. Based
on the simulation results, it is proved that deep learning models are better than
the statistical models. The authors in [6] used Restricted Boltzmann machine
and Rectified Linear Unit (ReLU) for training the data and electricity load
prediction respectively. Discrete wavelet transform and inconsistency rate meth-
ods are used for optimal feature selection from the features set in [7]. It helps
in dimensionality reduction. The parameter tuning of Support Vector Machine
(SVM) is performed using Sperm whale algorithm. Authors in [8]proposeda
model for STLF. In this work, for feature selection, Mutual Information (MI) is
used whereas, better prediction results are achieved by modifying the Artificial
Neural Network (ANN). Extreme Learning Machine (ELM) is used in [9]for
efficient load prediction.
The authors in [10] proposed an intelligent approach to forecast electricity
load using MI and ANN. In [11] the authors forecast electricity load and price
using enhanced CNN and enhanced SVM. ELM is a generalized single hidden
layer FFNN learning algorithm. It is proved to be effective for regression and
classification purposes. Authors used the Neural Network (NN) for achieving
better load prediction in [12]. Input weights and biases are randomly assigned
in ELM learning process, whereas output weights are calculated using Moore-
Penrose generalized inverse technique. Efficient load forecasting is performed
using sparse Bayesian ELM in [13]. This method is used for multi-classification
purpose. Authors in [14] used Particle Swarm Optimization (PSO) and discrete
PSO techniques for predicting day ahead electricity load. The Grey wolf opti-
mizer is used in combination with NN to optimize weights and biases in [15].
The simulation results proved that weights and biases optimization technique
improved the prediction accuracy. Back propagation technique is used for train-
ing ELM in [16]. Training is done using context neurons as input to hidden and
input layer of ELM. Authors in [17] enhanced RNN to achieve better prediction
accuracy by adjusting weights using previous iteration errors. Moreover, adjust-
ing biases and neurons selection also affects the prediction accuracy. The authors
in [18] developed a knowledge based system for STLF. In [19], 24 h ahead predic-
tion of cooling load of building is performed using deep learning. The simulation
Electricity Load Forecasting for Each Day of Week Using Deep CNN 1109
results showed that deep learning techniques improved the cooling load predic-
tion. Similarly in [20], RNN is used for electricity load prediction. In this work,
RNN groups the consumers into pool of inputs. It then handles the consumers
data as aggregated data, which reduces the computational time and resource
utilization.
1.1 Motivation and Problem Statement
The authors in [2] and [3] forecast electricity load using shallow NN by analysing
the historic load data. In [4], the authors used weather data to forecast the
electricity load demand using RNN. ELM is used to forecast the electricity load
demandin[16]. In [19], the cooling load of a residential building is forecasted
using a deep NN. The aforementioned work motivates us to forecast electricity
load using deep NN.
MLP is used in [2] and [3] for short term load forecasting. Similarity a single
layerFFNNisusedin[4] to forecast load. In [16], a back propagation technique
is used. Similarly, the authors in [19] used a deep RNN to forecast the load
demand of residential buildings. None of the above mentioned work used Deep
CNN (DCNN) to forecast electricity load demand for all days of the week.
1.2 Contribution
The main contribution of this paper are following:
An DCNN is proposed to forecast the electricity load of Victoria.
A performance comparison of the benchmark schemes with the proposed
scheme is performed.
The rest of this paper is organized as follows. Section 2is the proposed sys-
tem model. The proposed and existing schemes used to forecast electricity load
are discussed in Sect. 3. A detailed discussion on the simulation results of each
scheme is presented in Sect. 4. Section 5concludes the paper along with the
future directions of our work.
2SystemModel
Figure 3presents a complete picture of our proposed system model. Forecasting
electricity load belongs to the paradigm of Time Series (TS) forecasting. Accu-
rate load forecasting using TS data is not an easy task. Therefore, in this paper,
we have first converted the TS electricity load data into a supervised learning
problem. Afterwards, training and testing is performed to forecast the electricity
load using the proposed model.
To convert the TS electricity load data into a supervised learning problem, we
have first extracted all days of the week separately from the historical load data.
All Mondays are extracted to form a Monday group. Similarly, all Tuesdays are
extracted to form a Tuesday group etc. This processes is repeated for all days.
1110 S. Khan et al.
After the formation of seven groups, we further divide each group into a train
and test dataset sub-group. Every train data sub-group contains load data of
eight days. Whereas, the test dataset sub-group contains the load data of the
ninth day. After the formation of train and test data sub-groups, these groups
are appended one after the other in such a way that all Mondays are followed by
all Tuesdays, Similarly all Tuesdays are followed by Wednesdays etc. Once all
the days are grouped into one set of train and test dataset, we create the input
and output variables such that output to Xiis Xi+1 and output of Xnis X1.
The process of input and output variable formation is shown in Fig.1.
Monday
Tuesday t1 t2 ... n-1 n t1
Sunday t1 t2 ... n-1 n t1
t1 t2 ... n-1 n t1 Input variab les
Output
variables
Fig. 1. Input and output variables formation
2.1 Dataset Description
In this paper, the dataset released by the Australian energy market operator is
used to forecast the electricity load of Victoria. The dataset is publicly available
at [1]. In this paper, the dataset used for forecasting contains load data from the
last week of April 2018 till the second week of July 2018. The load values are
recorded after every thirty minutes in a day and there are forty eight observations
in one day. Figure 2shows the electricity load data used in this paper.
0500 1000 1500 2000 2500 3000
3500
5500
7500
Time (30 min interval)
Electricity load (MW)
Fig. 2. Electricity load of Victroia
Electricity Load Forecasting for Each Day of Week Using Deep CNN 1111
2.2 Performance Metrics
In forecasting the electricity load, researchers have used a number of performance
metric parameters. However, none of these performance evaluation metrics have
been marked as the standard parameters for evaluating the performance of a fore-
casting model. In order to evaluate, the effectiveness of our proposed scheme, we
used three performance metric parameters. These parameters are Mean Abso-
lute Percentage Error (MAPE), Mean Absolute Error (MAE) and Root Mean
Square Error (RMSE). Equations 1,2and 3presents the mathematical formula
of MAPE, MAE and RMSE respectively. Furthermore, to assess the performance
of each forecasting model, the lower the value of each performance metric metric
indicator, the higher the forecasting accuracy will be.
MAP E =(1
N
N
t=1
|XiYi
Yi
|)×100 (1)
MAE =1
N
N
t=1
|XiYi|2(2)
RM SE =
1
N
N
t=1
|XiYi|2(3)
Here Xipresents the actual load value, whereas, Yipresents the load forecast
values. To evaluate the forecasting results of a model, the lower the performance
metric parameter values, the better the results would be.
3 Existing and Proposed Forecasting Schemes
In this section we discussed the proposed and existing benchmark schemes used
to forecast the electricity load.
3.1 RNN
Among all the NN models, LSTM [21] is the most common type of RNN due
to its ability of memorizing information for a longer period of time. In LSTM,
every node act as a memory cell to store information. Furthermore, each node
has its own activation function. In order to process the input sequence, RNN
use the internal states. LSTM also have internal states, however, the difference
between other NN and LSTM is that in LSTM the old state becomes the input
to the next state along with the current input.
1112 S. Khan et al.
Start
Pre processing
Days extraction and dataset formation
Pre processing
Deep CNN structure
Selection of loss function
Selection of an activation function
Add hidden layers
Training and testing
Electricity load forecasting
Performance metrics
MAPE
MAE
RMSE
End
Parameter
tuni ng
Yes/No
Fig. 3. Proposed system model
3.2 CNN
The most successful type of neural network to solve various problems in medical
imaging and computer vision is CNN [25]. It is due to the fact that CNN can
handle large amount of input sequences. Furthermore, it has the ability to extract
the hidden features in the input data. The architecture of CNN comprises of
convolution, fully connected, dense, flatten and max pooling layers. Commonly,
the deeper the CNN model, the higher the accuracy will be. In this paper, CNN
has one convolution, one dropout and two dense layers.
Electricity Load Forecasting for Each Day of Week Using Deep CNN 1113
3.3 ARIMA
It is one of the most commonly used statistical technique for TS forecasting.
ARIMA as a TS forecasting model is proposed by Box and Jenkins [22]asa
combination of Auto Regression (AR) and Moving Average (MA). The key idea
to combine AR and MA is to approximate the real world representation in a
more accurate and precise way. The main advantage of using ARIMA to forecast
electricity load is that it can accurately forecast the future load values if the TS
is a stationary series. However, if the TS is not stationary, then the input series
is converted to a stationary TS by taking the first or second difference.
3.4 ELM
Huang et al. in [23] and [24] proposed ELM, which a type of feed forward neu-
ral network. Due to its generalization and learning abilities, ELM as forecast-
ing model has gained popularity in several fields. The core advantage of ELM
includes: (i) parameters of the hidden layers do not require fine tunning: (ii)
biasness and the input weights to ELM are randomly assigned.
3.5 DCNN
We enhance the forecasting performance of CNN by adding extra layers. Increas-
ing the number of layers in CNN scale up the size and complexity of the proposed
DCNN. However, in this work, our focus is to minimize the difference between
the actual and forecast values. The proposed DCNN comprises of convolution
and dense layers. A dropout layer at 20% along with ReLU activation function.
4 Simulation Results and Discussion
This section discusses the forecasting results. To affirm the usefulness of our
scheme, the proposed DCNN is compared with four benchmark schemes. To
better understand the forecasting behavior of each model, this section is further
divided in to five subsections.
4.1 Forecasting Results of RNN
The electricity load forecasted by RNN for Victoria is shown in Fig. 7. In this
figure, it can be clearly seen that there is a huge difference between the actual
and forecasted electricity load using RNN. From the performance metric graphs
showninFigs.4,5and 6it is concluded that RNN has the worst performance
in forecasting electricity load as compared to all the benchmark schemes used in
this paper. According to the performance metric values of RNN, Thursday has
the lowest error values. The minimum MAPE, MAE and RMSE values using
RNN to forecast electricity load of Victoria are 13.439%, 642.835 and 620.471
respectively. Furthermore, Monday has the worst performance metric values as
compare to all days of the week. To further study the usefulness of RNN in
forecasting electricity load of Victoria, the performance metric values for all
days of the week are displayed in Table 1.
1114 S. Khan et al.
ELM RNN DCNN CNN ARIMA
0
2
4
6
8
10
12
14
MAPE Scores
Mon
Tue
Wed
Thu
Fri
Sat
Sun
Fig. 4. MAPE of the five schemes using Victoria dataset
4.2 Forecasting Results of CNN
Figure 7shows the electricity load forecast of Victoria for all days using CNN.
As shown in this figure, the performance of CNN is slightly better as compare to
RNN. However, the difference in the forecasted and actual electricity is still very
large. The bar plots in Figs. 4,5and 6presents the performance errors metrics
of CNN. According to Table 1, CNN has the lowest error values in forecasting
the load of Thursday and Saturday. The MAPE, MAE and RMSE values for
CNN are 7.20%, 385.869 and 359.788 respectively. Whereas, in forecasting the
electricity load of Monday and Friday CNN has the worst performance metric
values.
ELM RNN DCNN CNN ARIMA
0
100
200
300
400
500
600
700
MAE Scores
Mon
Tue
Wed
Thu
Fri
Sat
Sun
Fig. 5. MAE of the five schemes using Victoria dataset
Electricity Load Forecasting for Each Day of Week Using Deep CNN 1115
4.3 Forecasting Results of ARIMA
According to Fig. 7, ARIMA achieved average results in forecasting electricity
load for Victoria as compare to CNN and RNN. Figure 7shows that at some time
slots the load forecasted by ARIMA is exactly the same as actual load. However,
at some time slots the load forecasted by ARIMA is totally unacceptable e.g., the
first time slot of Friday and Tuesday. According to the performance metric graphs
in Figs. 4,5and 6the performance of ARIMA in forecasting load for Victoria
is better on Wednesday as compare to other days of the week. The minimum
MAPE, MAE and RMSE achieved in forecasting electricity load by ARIMA for
Victoria is 3.58%, 238.154 and 194.830 respectively. Similarly, ARIMA has the
worst performance metric values in forecasting load of Tuesday.
ELM RNN DCNN CNN ARIMA
0
100
200
300
400
500
600
700
RMSE Sco res
Mon
Tue
Wed
Thu
Fri
Sat
Sun
Fig. 6. RMSE of the five schemes using Victoria dataset
4.4 Forecasting Results of ELM
Table 1presents the performance metric values of ELM for all days of the week.
AsshowninFig.7, ELM is the second best choice to forecast electricity load
for Victoria. From the performance metric graphs in Figs. 4,5and 6Wednesday
has the least error values. The MAPE, MAE and RMSE values for Wednesday
are 2.170%, 342.677 and 259.769 respectively. Similarly, ELM has the worst
performance metric values in forecasting electricity load of Monday.
4.5 Forecasting Results of DCNN
The performance metric graphs in Figs. 4,5and 6shows that the proposed
DCNN has the lowest performance metric values for all days of the week as
compare to all the benchmark schemes. According to Fig. 7, the load forecasted
by the proposed DCNN for Victoria almost overlaps the actual values for all
days of the week. Table 1shows the performance metric values for all days of the
week using Deep CNN. From this table, it can be clearly seen that the minimum
1116 S. Khan et al.
3500
5500
7500
Monda y
3500
5500
7500
Tues day
3500
5500
7500
Wednesday
3500
5500
7500
Thu rsd ay
3500
5500
7500
Fri d ay
3500
5500
7500
Sat u r da y
0 4 8 12 16 20 24
3500
5500
7500
Sun d ay
Hour (s)
Ele c t ri c it y l oa d ( MW )
DCNN
ARIMA
CNN
RNN
ELM
Act ual
Fig. 7. Forecasting results of all schemes for Victoria
Electricity Load Forecasting for Each Day of Week Using Deep CNN 1117
Table 1. Performance metric values
ELM RNN DCNN CNN ARIMA
MAPE
Monday 4.303 13.969 2.893 7.515 4.629
Tuesday 3.577 13.708 2.805 7.263 5.047
Wednesday 2.170 13.781 2.152 7.379 3.583
Thursday 2.606 13.439 2.489 7.370 3.984
Frid a y 3.846 13.937 2.705 7.609 4.633
Saturday 4.270 13.637 2.924 7.200 4.538
Sunday 4.017 13.787 2.927 7.370 4.578
MAE
Monday 342.677 767.183 218.879 469.614 347.052
Tuesday 271.484 732.568 201.115 441.339 352.144
Wednesday 152.037 683.748 138.771 401.976 238.154
Thursday 194.463 642.835 184.972 385.869 265.644
Frid a y 288.611 738.617 192.779 449.356 343.053
Saturday 336.182 752.452 218.885 455.808 351.269
Sunday 306.203 745.615 210.575 453.192 332.788
RMSE
Monday 259.769 732.158 171.732 415.240 273.986
Tuesday 209.630 701.686 162.286 392.409 293.096
Wednesday 117.390 666.721 116.417 376.971 194.830
Thursday 139.007 620.471 132.354 359.788 212.860
Frid a y 220.306 705.959 148.614 404.669 256.654
Saturday 256.228 716.093 172.620 399.010 266.153
Sunday 235.286 711.188 167.861 400.558 261.256
MAPE, MAE and RMSE in forecasting electricity load for Victoria are 2.15%,
138.771 and 116.417 respectively. Moreover, the lowest error values in forecasting
load using DCNN are achieved for Thursday. Similarly, the highest MAPE, MAE
and RMSE are 2.927%, 218.885 and 172.620. To sum up, by comparing the
usefulness of our proposed DCNN with the benchmark schemes, it can be said
that the proposed scheme has the best result in forecasting the electricity load
for all days.
5 Conclusion and Future Work
For utilities and generation companies, forecasting the actual demand of electric-
ity minimizes the power risk and production cost of electricity. NN are gaining
popularity in forecasting the electricity load demand because of their ability
1118 S. Khan et al.
to handle non linear and non stationary structure of the electricity load data.
In this paper, a DCNN is proposed to forecast the electricity load demand for
each day of week. Our experimental results illustrate that the proposed scheme
has the lowest MAPE, MAE and RMSE scores as compare to the benchmark
schemes. The proposed DCNN exceeds the existing benchmark schemes by scor-
ing the lowest MAPE, MAE and RMSE of 2.152%, 138.771 116.417. ELM has
the second best performance metric scores of 2.17, 152.037 and 117.390. ARIMA
achieved average results whereas, CNN and RNN has the worst performance
metric values. In future, we plan to investigate the impact of feature engineering
in forecasting the electricity load and price. Furthermore, to validate the effec-
tiveness of our proposed scheme, we plan to forecast the electricity load of other
states of Australia such as New South Wales and Queensland etc.
References
1. https://www.aemo.com.au/. Accessed 01 Jan 2019
2. Singh, S., Yassine, A.: Big data mining of energy time series for behavioral analytics
and energy consumption forecasting. Energies 11(2), 452 (2018)
3. Ahmad, T., Chen, H.: Short and medium-term forecasting of cooling and heating
load demand in building environment with data-mining based approaches. Energy
Build. 166, 460–476 (2018)
4. Chen, K., Chen, K., Wang, Q., He, Z., Hu, J., He, J.: Short-term load forecasting
with deep residual networks. IEEE Trans. Smart Grid (2018)
5. Jesus, L., De Ridder, F., De Schutter, B.: Forecasting spot electricity prices: Deep
learning approaches and empirical comparison of traditional algorithms. Appl.
Energy 221, 386–405 (2018)
6. Ryu, S., Noh, J., Kim, H.: Deep neural network based demand side short term load
forecasting. Energies 10(1), 3 (2016)
7. Liu, J., Li, C.: The short-term power load forecasting based on sperm whale algo-
rithm and wavelet least square support vector machine with DWT-IR for feature
selection. Sustainability 9(7), 1188 (2017)
8. Ashfaq, A., Javaid, N., Guizani, M., Alrajeh, N., Khan, Z.A.: An accurate and fast
converging short-term load forecasting model for industrial applications in a smart
grid. IEEE Trans. Ind. Inform. 13(5), 2587–2596 (2017)
9. Huang, G.-B., Zhou, H., Ding, X., Zhang, R.: Extreme learning machine for regres-
sion and multiclass classification. IEEE Trans. Syst. Man Cybern. Part B (Cybern.)
42(2), 513–529 (2012)
10. Ahmad, A., Javaid, N., Mateen, A., Awais, M., Khan, Z.: Short-term load forecast-
ing in smart grids: an intelligent modular approach. Energies 12(1), 164 (2019)
11. Zahid, M., Ahmed, F., Javaid, N., Abbasi, R.A., Kazmi, H.S.Z., Javaid, A., Bilal,
M., Akbar, M., Ilahi, M.: Electricity price and load forecasting using enhanced
convolutional neural network and enhanced support vector regression in smart
grids. Electronics 8(2), 122 (2019)
12. Fallah, S., Deo, R., Shojafar, M., Conti, M., Shamshirband, S.: Computational
intelligence approaches for energy load forecasting in smart energy management
grids: state of the art, future challenges, and research directions. Energies 11(3),
596 (2018)
13. Luo, J., Vong, C.-M., Wong, P.-K.: Sparse Bayesian extreme learning machine for
multi-classification. IEEE Trans. Neural Netw. Learn. Syst. 25(4), 836–843 (2014)
Electricity Load Forecasting for Each Day of Week Using Deep CNN 1119
14. Yu, J., Wang, S., Xi, L.: Evolving artificial neural networks using an improved PSO
and DPSO. Neurocomputing 71(4–6), 1054–1060 (2008)
15. Zeng, Y.-R., Zeng, Y., Choi, B., Wang, L.: Multifactor-influenced energy consump-
tion forecasting using enhanced back-propagation neural network. Energy 127,
381–396 (2017)
16. Saremi, S., Mirjalili, S.Z., Mirjalili, S.M.: Evolutionary population dynamics and
grey wolf optimizer. Neural Comput. Appl. 26(5), 1257–1263 (2015)
17. Ertugrul, ¨
O.F.: Forecasting electricity load by a novel recurrent extreme learning
machines approach. Int. J. Electr. Power Energy Syst. 78, 429–435 (2016)
18. Khan, M., Javaid, N., Naseem, A., Ahmed, S., Riaz, M., Akbar, M., Ilahi, M.:
Game theoretical demand response management and short-term load forecasting
by knowledge based systems on the basis of priority index. Electronics 7(12), 431
(2018)
19. Fan, C., Xiao, F., Zhao, Y.: A short-term building cooling load prediction method
using deep learning algorithms. Appl. Energy 195, 222–233 (2017)
20. Shi, H., Minghao, X., Li, R.: Deep learning for household load forecasting-a novel
pooling deep RNN. IEEE Trans. Smart Grid 9(5), 5271–5280 (2018)
21. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8),
1735–1780 (1997)
22. Box, G.E.P., Jenkins, G.M., Reinsel, G.C., Ljung, G.M.: Time Series Analysis:
Forecasting and Control. Wiley, Hoboken (2015)
23. Huang, G.-B., Zhu, Q.-Y., Siew, C.-K.: Extreme learning machine: a new learning
scheme of feedforward neural networks. In: 2004 Proceedings of the IEEE Interna-
tional Joint Conference on Neural Networks, vol. 2, pp. 985–990. IEEE (2004)
24. Huang, G.-B., Chen, L., Siew, C.K.: Universal approximation using incremental
constructive feedforward networks with random hidden nodes. IEEE Trans. Neural
Netw. 17(4), 879–892 (2006)
25. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep con-
volutional neural networks. In: Advances in Neural Information Processing Sys-
tems, pp. 1097–1105 (2012)
... The architectural designs of DL techniques, such as LSTM and 1D CNN, are able to perform internal feature extraction in order to minimize the forecasting error: LSTM is used for short-term forecasting of the electric load in [13]. By using 1D CNN, Reference [14] forecasts the daily electricity load. Moreover, a hybrid of 1D CNN and LSTM is used for forecasting Particulate Matter concentration in smart cities in [15]. ...
... 13 We calculate the performance of the forecaster at each fold f and compute the mean performance over all of the folds. At each fold f , during training, we minimize the Mean Absolute Error (MAE) for the VBP class, and the Categorical Cross-Entropy for the VBA and the FBA classes 14 . In order to prevent overfitting, instead of using a fixed number of epochs, we use a variable number of epochs across all of the folds of any given data set. ...
... That is, by the end of the CV, we have use each subset nine times as the training set and exactly once as the test set. 14 We use softmax at the output of the forecaster for the VBA and the FBA classes. As a result, we minimize the Categorical Cross-Entropy for the misclassification error between the output classes that are constituted by the distinct number of bits that a sensor can generate. ...
Article
Full-text available
We develop a novel end-to-end trainable feature selection-forecasting (FSF) architecture for predictive networks targeted at the Internet of Things (IoT). In contrast with the existing filter-based, wrapper-based and embedded feature selection methods, our architecture enables the automatic selection of features dynamically based on feature importance score calculation and gamma-gated feature selection units that are trained jointly and end-to-end with the forecaster. We compare the performance of our FSF architecture on the problem of forecasting IoT device traffic against the following existing (feature selection, forecasting) technique pairs: Autocorrelation Function (ACF), Analysis of Variance (ANOVA), Recurrent Feature Elimination (RFE) and Ridge Regression methods for feature selection, and Linear Regression, Multi-Layer Perceptron (MLP), Long Short Term Memory (LSTM), 1 Dimensional Convolutional Neural Network (1D CNN), Autoregressive Integrated Moving Average (ARIMA), and Logistic Regression for forecasting. We show that our FSF architecture achieves either the best or close to the best performance among all of the competing techniques by virtue of its dynamic, automatic feature selection capability. In addition, we demonstrate that both the training time and the execution time of FSF are reasonable for IoT applications. This work represents a milestone for the development of predictive networks for IoT in smart cities of the near future.
... Another study presented by Khan et al. [7] using smart grid to predict load each day of week in Victoria in Australia. The proposed new approach is using Deep Convolutional Neural Networks (DCNN) to forecast the load for similar days of several weeks. ...
Conference Paper
An assessment of wind speed and prediction of output power from a wind machine is important before implementing either commercial power plants or a standalone project. There are many studies targeting the improvement of wind power predictions and have achieved a desirable performance. This paper was conducted with the aim of obtaining accurate wind power production and leveraging the probability of reducing dependency on fossil fuels in the Kingdom of Saudi Arabia (KSA). The data of wind speed was collected from the Weather Online service (WO Service) to do the assessment for the city of Yanbu in KSA for two years. We have used four machine learning techniques in our proposed research to produce four models. Convolutional Neural Network (CNN), Multi-Layer Perceptron (MLP), Super Vector Machine (SVM), and Gaussian Naive Bayes (GNB) were used within these models to evaluate the hourly wind speed and the wind turbine output power. The results of the four trained models show the estimated output power of 2 Megawatt (MW) from the wind. The CNN model showed the best performance since the mean absolute error was 0:011, the test accuracy was 99:9886% and the predicted power was 7431:5 MW while the actual power is 7; 432:28 MW. Index Terms—Wind Energy, Power Prediction, Machine Learning, Convolutional Neural Network, Support Vector Machine, Multi-Layer Perceptron, Gaussian Na¨ıve Bayer
... In addition, ARIMA model also shows the outstanding performance in forecasting tasks such as dengue forecasting [15], soybean production forecasting [16], medical cases forecasting [17], electricity load forecasting [18], wind speed forecasting [19], etc. Since hybridization methods able to produce great performance recently, researchers concern on the combination of ARIMA with neural network or deep learning approach to enhance the performance in engineering problems. ...
Conference Paper
Full-text available
Machine Learning (ML) and Deep Neural Network (DNN) based Computer-aided decision (CAD) systems show the effective implementation in solving skin cancer classification problem. However, ML approach unable to get the deep features from network flow which causes the low accuracy performance and the DNN model has the complex network with an enormous number of parameters that resulting in the limited classification accuracy. In this paper, the hybrid Convolutional Neural Network algorithm and Autoregressive Integrated Moving Average model (CNN-ARIMA) have been proposed to classify three different types of skin cancer. The proposed CNN-ARIMA able to classify skin cancer image successfully and achieved test accuracy, average sensitivity, average specificity, average precision and AUC of 96.00%, 96.02%, 97.98%, 96.13% and 0.995, respectively which outperformed the state-of-art methods.
... [28] developed a CNN-based methodology for electricity load forecasting and compared their results with a factored restricted Boltzmann machine, sequence-to-sequence long short term memory (LSTM), support vector regressor (SVR), and ANN. Another study presented in [29] proposed a deep CNN network for day-ahead load forecasting and compared the results with an extreme learning machine, ARIMA, CNN, and RNN. Several studies also used RNN models for electricity load prediction, whereas Tokgoz et al. [30] used RNN, gated recurrent unit (GRU), and LSTM models for electricity load prediction in Turkey and extensively decreased the error. ...
Article
Full-text available
Smart grid technology based on renewable energy and energy storage systems are attracting considerable attention towards energy crises. Accurate and reliable model for electricity prediction is considered a key factor for a suitable energy management policy. Currently, electricity consumption is rapidly increasing due to the rise in human population and technology development. Therefore, in this study, we established a two-step methodology for residential building load prediction, which comprises two stages: in the first stage, the raw data of electricity consumption are refined for effective training; and the second step includes a hybrid model with the integration of convolutional neural network (CNN) and multilayer bidirectional gated recurrent unit (MB-GRU). The CNN layers are incorporated into the model as a feature extractor, while MB-GRU learns the sequences between electricity consumption data. The proposed model is evaluated using the root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE) metrics. Finally, our model is assessed over benchmark datasets that exhibited an extensive drop in the error rate in comparison to other techniques. The results indicated that the proposed model reduced errors over the individual household electricity consumption prediction (IHEPC) dataset (i.e., RMSE (5%), MSE (4%), and MAE (4%)), and for the appliances load prediction (AEP) dataset (i.e., RMSE (2%), and MAE (1%)).
Article
The reliable and an economic operation of the power system rely on an accurate prediction of short term load. In this paper, a deep learning based Long Short Term Memory (LSTM) with hybrid feature selection namely RMR-HFS-LSTM, is proposed. The objective of this study is to reduce the curse of dimensionality, reduce the overfitting and improve the accuracy of short term load forecasting. The RMR-HFS is a combination of filter and wrapper feature selection introduced for identifying optimal subset of features. The instance based RReliefF and information theoretic based mutual information filter feature selection are utilized to reduce curse of dimensionality by finding and eliminating irrelevant features. The selected features of filter feature selection is tuned by using Recursive Feature Elimination (RFE) wrapper feature selection to reduce overfitting. The deep learning based LSTM improves the accuracy by handling uncertainty issues. The experiment was conducted on European weather and electricity load data using python on Tensorflow environment. The performance of the proposed RMR-HFS-LSTM model is compared against Multilayer Perceptron (MLP) and Recurrent Neural Network (RNN) in terms of Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). The result shows that the proposed RMR-HFS-LSTM model outperforms other models.
Article
With the development of smart grids and the popularization of smart meters, grid companies have obtained a large amount of fine-grained user electricity consumption data, making it possible to forecast individual users’ electricity load. Traditional deterministic forecasting cannot measure the uncertainty of users’ future electricity consumption behavior. This paper aims to establish a short-term load probability forecasting model for individual users, which can output the probability prediction interval and the probability density curve. Firstly, historical data is applied to train a deterministic prediction model based on random forest. Then, when predicting the user load at a future time, the output of each tree in the forest is formed into a prediction set, and the kernel density estimation method is used to obtain the probability prediction result of the user load. The proposed RF-KDE method obtains promising results on a public dataset. It also shows the advantages of easy parameters adjustment and fast training speed. Besides, tests conducted on the public dataset confirm that the proposed method can be applied to users with different electricity consumption behaviors.
Article
The high-level variation of different energy generation resources makes the reliable power supply significantly challenging to end-users. These variations occur due to the intermittent nature of energy output and time-varying weather conditions. The recent literature focus on the improvements in power generation and consumption forecasting results, which is a demand of the current smart grids’ smooth operations with a balanced amount of energy generation and consumption for the connected customers. Inspired by the applications of load forecasting, therefore, in this work, we develop an efficient and effective hybrid model for power generation and consumption forecasting, thereby contributing to energy harvesting by providing valuable prediction data to the concerned renewable energy analysts. Herein, we integrate a convolutional layered network with an echo state network for robust renewable energy and consumption forecasting. The convolutional network is used to extract meaningful patterns from the historical data which is then forwarded to the echo state network for temporal features learning. The output spatiotemporal feature vector is then fed to fully connected layers for final forecasting. The proposed hybrid model is derived after extensive experiments over machine learning and deep learning, where the results indicate that the proposed model substantially decrease the forecasting errors metrics such as RMSE, MSE, NRMSE, and MAE when compared to state-of-the-art models and acts as a paradigm towards energy equilibrium between production resources and consumers.
Article
In modern power systems, centralised short term load forecasting (STLF) methods raise concern on high communication requirements and reliability when a central controller undertakes the processing of massive load data solely. As an alternative, distributed methods avoid the problems mentioned above, whilst the possible issues of cyberattacks and uncertain forecasting accuracy still exist. To address the two issues, a novel distributed deep belief networks (DDBN) with Markovian switching topology is proposed for an accurate STLF, based on a completely distributed framework. Without the central governor, the load dataset is separated and the model is trained locally, while obtaining the updates through communication with stochastic neighbours under a designed consensus procedure, and therefore significantly reduced the training time. The overall network reliability against cyberattacks is enhanced by continually switching communication topologies. In the meanwhile, to ensure that the distributed structure is still stable under such a varying topology, the consensus controller gain is delicately designed, and the convergence of the proposed algorithm is theoretically analysed via the Lyapunov function. Besides, restricted Boltzmann machines (RBM) based unsupervised learning is employed for DDBN initialisation and thereby guaranteeing the success rate of STLF model training. GEFCom 2017 competition and ISO New England load datasets are applied to validate the accuracy and effectiveness of the proposed method. Experiment results demonstrate that the proposed DDBN algorithm can enhance around 19% better forecasting accuracy than centralised DBN algorithm.
Article
Load forecasting is of crucial importance for operations of electric power systems. In recent years, deep learning based methods are emerging for load forecasting because their strong nonlinear approximation capabilities can provide more forecasting precision than conventional statistical methods. However, they usually suffer from some problems, e.g., the gradient vanishment and over-fitting. In order to address these problems, an unshared convolution based deep learning model with densely connected network is proposed. In this model, the backbone is the unshared convolutional neural network and a densely connected structure is adopted, which could alleviate the gradient vanishment. What is more, we use a regularization method named clipped $L_2$ -norm to overcome over-fitting, and design a trend decomposition strategy to address the possible distribution differences between the training and validation data. Finally, we conduct five case studies to verify the outperformance of our proposed deep learning model for deterministic and interval load forecasting. Two high-voltage and an medium-voltage real load datasets from Australia, Germany and America are used for model training and validation, respectively. Results show that the proposed model can achieve higher load forecasting accuracy, compared with other existing methods including the popular conventional methods such as naive forecast and generalized additive model, and deep learning methods, e.g., long short-term memory network, convolutional neural network, fully connected network, etc.
Article
Full-text available
Short-Term Electricity Load Forecasting (STELF) through Data Analytics (DA) is an emerging and active research area. Forecasting about electricity load and price provides future trends and patterns of consumption. There is a loss in generation and use of electricity. So, multiple strategies are used to solve the aforementioned problems. Day-ahead electricity price and load forecasting are beneficial for both suppliers and consumers. In this paper, Deep Learning (DL) and data mining techniques are used for electricity load and price forecasting. XG-Boost (XGB), Decision Tree (DT), Recursive Feature Elimination (RFE) and Random Forest (RF) are used for feature selection and feature extraction. Enhanced Convolutional Neural Network (ECNN) and Enhanced Support Vector Regression (ESVR) are used as classifiers. Grid Search (GS) is used for tuning of the parameters of classifiers to increase their performance. The risk of over-fitting is mitigated by adding multiple layers in ECNN. Finally, the proposed models are compared with different benchmark schemes for stability analysis. The performance metrics MSE, RMSE, MAE, and MAPE are used to evaluate the performance of the proposed models. The experimental results show that the proposed models outperformed other benchmark schemes. ECNN performed well with threshold 0.08 for load forecasting. While ESVR performed better with threshold value 0.15 for price forecasting. ECNN achieved almost 2% better accuracy than CNN. Furthermore, ESVR achieved almost 1% better accuracy than the existing scheme (SVR).
Article
Full-text available
Daily operations and planning in a smart grid require a day-ahead load forecasting of its customers. The accuracy of day-ahead load-forecasting models has a significant impact on many decisions such as scheduling of fuel purchases, system security assessment, economic scheduling of generating capacity, and planning for energy transactions. However, day-ahead load forecasting is a challenging task due to its dependence on external factors such as meteorological and exogenous variables. Furthermore, the existing day-ahead load-forecasting models enhance forecast accuracy by paying the cost of increased execution time. Aiming at improving the forecast accuracy while not paying the increased executions time cost, a hybrid artificial neural network-based day-ahead load-forecasting model for smart grids is proposed in this paper. The proposed forecasting model comprises three modules: (i) a pre-processing module; (ii) a forecast module; and (iii) an optimization module. In the first module, correlated lagged load data along with influential meteorological and exogenous variables are fed as inputs to a feature selection technique which removes irrelevant and/or redundant samples from the inputs. In the second module, a sigmoid function (activation) and a multivariate auto regressive algorithm (training) in the artificial neural network are used. The third module uses a heuristics-based optimization technique to minimize the forecast error. In the third module, our modified version of an enhanced differential evolution algorithm is used. The proposed method is validated via simulations where it is tested on the datasets of DAYTOWN (Ohio, USA) and EKPC (Kentucky, USA). In comparison to two existing day-ahead load-forecasting models, results show improved performance of the proposed model in terms of accuracy, execution time, and scalability.
Article
Full-text available
The emergence of the Demand Response (DR) program optimizes the energy consumption pattern of customers and improves the efficacy of energy supply. The pricing infra-structure of the DR program is dynamic (time-based). It has rather complex features including marginal costs, demand and seasonal parameters. There is variation in DR price rate. Sometime prices go high (peak load) if the demand of electricity is more than the generation capacity. The main objective of DR is to encourage the consumer to shift the peak load and gets incentives in terms of cost reduction. However, prices remain the same for all the users even if they shift the peak load or not. In this work, Game Theory (GT)-based Time-of-Use (ToU) pricing model is presented to define the rates for on-peak and shoulder-peak hours. The price is defined for each user according to the utilize load. At first, the proposed model is examined using the ToU pricing scheme. Afterward, it is evaluated using existing day-ahead real-time pricing scheme. Moreover, shifting load from on-peak hours to off-peak hours may cause rebound peak in off-peak hours. To avert this issue, we analysis the impact of Salp Swam Algorithm (SSA) and Rainfall Algorithm (RFA) on user electricity bill and PAR after scheduling. The experimental results show the effectiveness of the proposed GT-based ToU pricing scheme. Furthermore, the RFA outperformed SSA.
Article
Full-text available
Demand Response Management (DRM) is considered one of the crucial aspects of the smart grid as it helps to lessen the production cost of electricity and utility bills. DRM becomes a fascinating research area when numerous utility companies are involved and their announced prices reflect consumer’s behavior. This paper discusses a Stackelberg game plan between consumers and utility companies for efficient energy management. For this purpose, analytical consequences (unique solution) for the Stackelberg equilibrium are derived. Besides this, this paper presents a distributed algorithm which converges for consumers and utilities. Moreover, different power consumption activities on the basis of time series are becoming a basic need for load prediction in smart grid. Load forecasting is taken as the significant concerns in the power systems and energy management with growing technology. The better precision of load forecasting minimizes the operational costs and enhances the scheduling of the power system. The literature has discussed different techniques for demand load forecasting like neural networks, fuzzy methods, Naïve Bayes, and regression based techniques. This paper presents a novel knowledge based system for short-term load forecasting. The algorithms of Affinity Propagation and Binary Firefly Algorithm are integrated in knowledge based system. Besides, the proposed system has minimum operational time as compared to other techniques used in the paper. Moreover, the precision of the proposed model is improved by a different priority index to select similar days. The similarity in climate and date proximity are considered all together in this index. Furthermore, the whole system is distributed in sub-systems (regions) to measure the consequences of temperature. Additionally, the predicted load of the entire system is evaluated by the combination of all predicted outcomes from all regions. The paper employs the proposed knowledge based system on real time data. The proposed scheme is compared with Deep Belief Network and Fuzzy Local Linear Model Tree in terms of accuracy and operational cost. In addition, the presented system outperforms other techniques used in the paper and also decreases the Mean Absolute Percentage Error (MAPE) on a yearly basis. Furthermore, the novel knowledge based system gives more efficient outcomes for demand load forecasting.
Article
Full-text available
A demand response (DR) based home energy management systems (HEMS) synergies with renewable energy sources (RESs) and energy storage systems (ESSs). In this work, a three-step simulation based posteriori method is proposed to develop a scheme for eco-efficient operation of HEMS. The proposed method provides the trade-off between the net cost of energy ( C E n e t ) and the time-based discomfort ( T B D ) due to shifting of home appliances (HAs). At step-1, primary trade-offs for C E n e t , T B D and minimal emissions T E M i s s are generated through a heuristic method. This method takes into account photovoltaic availability, the state of charge, the related rates for the storage system, mixed shifting of HAs, inclining block rates, the sharing-based parallel operation of power sources, and selling of the renewable energy to the utility. The search has been driven through multi-objective genetic algorithm and Pareto based optimization. A filtration mechanism (based on the trends exhibited by T E M i s s in consideration of C E n e t and T B D ) is devised to harness the trade-offs with minimal emissions. At step-2, a constraint filter based on the average value of T E M i s s is used to filter out the trade-offs with extremely high values of T E M i s s . At step-3, another constraint filter (made up of an average surface fit for T E M i s s ) is applied to screen out the trade-offs with marginally high values of T E M i s s . The surface fit is developed using polynomial models for regression based on the least sum of squared errors. The selected solutions are classified for critical trade-off analysis to enable the consumer choice for the best options. Furthermore, simulations validate our proposed method in terms of aforementioned objectives.
Article
Full-text available
We present in this paper a model for forecasting short-term electric load based on deep residual networks. The proposed model is able to integrate domain knowledge and researchers' understanding of the task by virtue of different neural network building blocks. Specifically, a modified deep residual network is formulated to improve the forecast results. Further, a two-stage ensemble strategy is used to enhance the generalization capability of the proposed model. We also apply the proposed model to probabilistic load forecasting using Monte Carlo dropout. Three public datasets are used to prove the effectiveness of the proposed model. Multiple test cases and comparison with existing models show that the proposed model is able to provide accurate load forecasting results and has high generalization capability.
Article
Full-text available
In this paper, we address the problem of minimizing the total daily energy cost in a smart residential building composed of multiple smart homes with the aim of reducing the cost of energy bills and the greenhouse gas emissions under different system constraints and user preferences. As the household appliances contribute significantly to the energy consumption of the smart houses, it is possible to decrease electricity cost in buildings by scheduling the operation of domestic appliances. In this paper, we propose an optimization model for jointly minimizing electricity costs and CO2 emissions by considering consumer preferences in smart buildings that are equipped with distributed energy resources (DERs). Both controllable and uncontrollable tasks and DER operations are scheduled according to the real-time price of electricity and a peak demand charge to reduce the peak demand on the grid. We formulate the daily energy consumption scheduling problem in multiple smart homes from economic and environmental perspectives and exploit a mixed integer linear programming technique to solve it. We validated the proposed approach through extensive experimental analysis. The results of the experiment show that the proposed approach can decrease both CO2 emissions and the daily energy cost.
Article
Full-text available
The increasing demand for electricity and the emergence of smart grids have presented new opportunities for a home energy management system (HEMS) that can reduce energy usage. HEMS incorporates a demand response (DR) tool that shifts and curtails demand to improve home energy consumption. This system commonly creates optimal consumption schedules by considering several factors, such as energy costs, environmental concerns, load profiles, and consumer comfort. With the deployment of smart meters, performing load control using HEMS with DR-enabled appliances has become possible. This paper provides a comprehensive review on previous and current research related to HEMS by considering various DR programs, smart technologies, and load scheduling controllers. The application of artificial intelligence for load scheduling controllers, such as artificial neural network, fuzzy logic, and adaptive neural fuzzy inference system, is also reviewed. Heuristic optimization techniques, which are widely used for optimal scheduling of various electrical devices in a smart home, are also discussed.
Article
Full-text available
In this paper, a novel modeling framework for forecasting electricity prices is proposed. While many predictive models have been already proposed to perform this task, the area of deep learning algorithms remains yet unexplored. To fill this scientific gap, we propose four different deep learning models for predicting electricity prices and we show how they lead to improvements in predictive accuracy. In addition, we also consider that, despite the large number of proposed methods for predicting electricity prices, an extensive benchmark is still missing. To tackle that, we compare and analyze the accuracy of 27 common approaches for electricity price forecasting. Based on the benchmark results, we show how the proposed deep learning models outperform the state-of-the-art methods and obtain results that are statistically significant. Finally, using the same results, we also show that: (i) machine learning methods yield, in general, a better accuracy than statistical models; (ii) moving average terms do not improve the predictive accuracy; (iii) hybrid models do not outperform their simpler counterparts.
Article
Full-text available
Demand side management (DSM) in smart grid authorizes consumers to make informed decisions regarding their energy consumption pattern and helps the utility in reducing the peak load demand during an energy stress time. This results in reduced carbon emission, consumer electricity cost, and increased grid sustainability. Most of the existing DSM techniques ignore priority defined by consumers. In this paper, we present priority-induced DSM strategy based on the load shifting tech-nique considering various energy cycles of an appliance. The day-ahead load shifting technique proposed is mathematically formulated and mapped to multiple knapsack problem to mitigate the rebound peaks. The autonomous energy management controller proposed embeds three meta-heuristic optimization techniques; genetic algorithm, enhanced differential evolu-tion, and binary particle swarm optimization along with optimal stopping rule, which is used for solving the load shifting problem. Simulations are carried out using three different appliances and the results validate that the proposed DSM strategy successfully shifts the appliance operations to off-peak time slots, which consequently leads to substantial electricity cost savings in reasonable waiting time, and also helps in reducing the peak load demand from the smart grid. In addition, we calculate the feasible regions to show the relationship between cost, energy consumption, and delay. A priority-induced demand side management system to mitigate rebound peaks using multiple knapsack. Available from: https://www.researchgate.net/publication/323945280_A_priority-induced_demand_side_management_system_to_mitigate_rebound_peaks_using_multiple_knapsack [accessed Mar 26 2018].