Conference PaperPDF Available

Data Analytics for Short Term Price and Load Forecasting in Smart Grids using Enhanced Recurrent Neural Network



In this paper, an artificial neural network (ANN)based methodology is proposed to forecast electricity load and price. The performance of an ANN forecast model depends on appropriate input parameters. Parameter tuning of ANN is very important to increase the accuracy of electricity price and load prediction. This is done using mutual information and decision tree. After selecting best features for forecasting, these features are given to forecasting engine working on principles of recurrent neural network (RNN). For simulations, data set is taken from national electricity market (NEM), Australia. Results show that the methodology has increased the accuracy of electricity load and price forecast. Whereas, the error rate of forecasting is lower than the other models for electricity load and price.
Data Analytics for Short Term Price and Load
Forecasting in Smart Grids using Enhanced
Recurrent Neural Network
Muhammad Usman1, Zahoor Ali Khan2, Inam Ullah Khan3, Sakeena Javaid1and Nadeem Javaid1,
1COMSATS University Islamabad, Islamabad 44000, Pakistan
2CIS, Higher Colleges of Technology, Fujairah 4114, United Arab Emirates
3COMSATS University Islamabad, Lahore 54000, Pakistan
Abstract—In this paper, an artificial neural network (ANN)
based methodology is proposed to forecast electricity load and
price. The performance of an ANN forecast model depends on
appropriate input parameters. Parameter tuning of ANN is very
important to increase the accuracy of electricity price and load
prediction. This is done using mutual information and decision
tree. After selecting best features for forecasting, these features
are given to forecasting engine working on principles of recurrent
neural network (RNN). For simulations, dataset is taken from
national electricity market (NEM), Australia. Results show that
the methodology has increased the accuracy of electricity load
and price forecast. Whereas, the error rate of forecasting is lower
than the other models for electricity load and price.
Index Terms—Smart grid, Data analytics, Artificial neural
network, Long short term memory, Forecasting, Short term
With the passage of time, human population is increasing
significantly with which demand of electricity also increases.
To meet such huge demand of electricity traditional grid are not
efficient. Due to poor performance and increasing maintenance
cost of traditional grid electricity prices also increased. To
overcome the limitation of traditional grid smart grids (SG) are
introduced. Success of smart girds relies on the information
they gather. If SG has good quality of data then it become easy
to forecast load demand and price through different techniques.
As it is known excess electricity generation results in high
cost therefore system operators must know how much energy
is to generate during certain periods to meet the demand and
not exceed this demand significantly. Precisely predicting
load and price can provide useful information to reduce the
generation and maintenance costs and help in planing and
operations of a SG. With the help of data analytics in SG
extracting useful information become easier this information
helps in forecasting. With the help of data analysis on big
data previously unknown hidden patterns,energy consumption
trends and other important information is extracted. The term
big data refers to huge amount of data [
]. Big data have some
characteristics which are refereed as 4 V’s of big data:
Volume refers to huge amount of data generated. Huge amount
of data from grid and smart meters are recorded every minute.
1Prediction and forecasting are used alternatively
Velocity refers to speed at which new data is generated. Data
is recorded a very high speed in girds having sensitive sensor.
Variety refers to different type of data like structured and
unstructured data. Data from different sensor and devices are
also recorded.
Veracity refers to accuracy or trustworthiness of the data.
In data analytics different techniques are used on data. There
are different classifier for prediction which are used in field
of data analytics to extract useful in formation. GS used these
techniques for prediction of load demand. artificial neural
network (ANN) techniques are very helpful in when dealing
when big data because they have computational power to handle
big data and it gives better results.
A. Problem Statement and Contributions
In ANN, there are many classifiers which are used for
forecasting. One of them is recurrent neural network (RNN),
which is usually used for text generation. The basic problem
in RNN is gradient vanishing and gradient exploding. Model
is not properly trained and layered in the beginning of the
neural network and do not give good prediction due to these
two problems [
]. Vanishing gradient is a problem in which
gradient based learning algorithms found difficulty in training
network. In gradient based learning algorithm, weights are
updated in each epoch by taking partial derivative of the error
with respect to its weight. In some cases, gradient become
too small after sufficient iteration that it prevents the weight
from updation. Sometimes training completely stops due to
vanishing gradient. There is another problem in RNN that
it can not process log sequences of input and it can not be
used in deep neural networks (DNNs) because of activation
function used in RNN. Activation functions like tanh contribute
in loss of gradient [
]. To overcome the limitations of RNN,
an enhanced recurrent neural network (ERNN) is proposed to
address these problems in this work.
In this paper, we highlight the electricity price and load
forecasting problem. The objective of our work is to predict
the accurate load and price using data analytics on SG. To
solve this problem, we have applied RNN to forecast load
and price. RNN is a classifier that uses its previous hidden
states to predict next state. There are different parameters in
RNN, which are used for tuning purpose. RNN is a good
classifier; however, challenges are needed to overcome its
accuracy. Many techniques have been proposed over the last
years, both statistical and machine learning [
]. In this
paper, an enhanced RNN is used, which is the combination
of long short term memory (LSTM) and FFNN to increase
efficiency and to give better results. This paper proposes a
comprehensive load and price forecasting method based on
RNN, which can generate complete map of future demand. The
obtained results from two case studies show that the quality
of forecasting has been significantly improved as compared to
FFNN and RNN models.
In this section detail description of techniques are given
which is used in the proposed model shown in Fig. 1 to forecast
load and price. As it is known NEM dataset is used in this
system. Step wise description of techniques are as follows.
A. Feature Selection and Extraction
In first step, 2 stage feature selection, decision tree and
recursive feature elimination (RFE), is used. Decision tree (DT)
algorithm is very popular it is computationally fast. Besides
forming interpretable classification rules it can select features
on its own. DT tells about all possible outcomes. DT helps
in determining worst, best and expected values for different
scenarios. It can also combine with other decision techniques.
In second step, conditional mutual information (CMI) is used
for feature extraction. MI is the one of the most effective
techniques for feature extraction. However, sometimes it not
easy to get accurate estimation for high dimensional data.
The optimal feature extraction, in case of MI, is done when
a feature is created from a feature set where two features
are the least important for the value of the target and have
high redundancy among each other. In RFE, most important
features are selected from feature vector by reducing feature
set model become computationally fast. RFE reduce dimension
and redundancy of features. Which is common method for
removing redundancy.
B. Enhanced Recurrent Neural Network(ERNN) Prediction
Recurrent neural network (RNN) is used for price and load
forecasting. RNN are the state of the art algorithm because
it is the first algorithm that remembers its input, due to an
internal memory. In RNN information cycle through a loop
means that hidden state of cell is also input for next cell with
its input which hepls RNN to make better decision, it takes into
consideration the current input and also what it has learned from
the input it received previously which make it perfectly suited
for machine learning problems with sequential data. There are
some limitations in RNN like vanishing and exploding gradient
due to which training of deep RNN is difficult. RNN also can
not deal with long sequence of data.
For forecasting of load and price in this paper ERNN is
used. which is an enhanced form of RNN. Purpose of using
enhanced scheme is that in RNN there is a problem of vanishing
gradient and RNN can not remember long sequences of input
so predicting ahead becomes difficult. In vanishing gradient
the value of gradient become to small that is does not train
the layers at the beginning properly. In LSTM there cell initial
state and hidden state initialized as zero then for every input
we call LSTM cell to which hidden state and cell state is
given with current input. Previous hidden state and current
input is combined and stored in combine then combine is given
to forget layer. In forget layer irrelevant data is removed. A
candidate layer is added using combine . This layer have values
which are added to cell state. Combine layer is also given to
input layer. This layer decide which values should be added
to new cell state. when forget layer, candidate layer and the
input layer is computed then cell state is calculated. In the end
output is calculated. point-wise multiplication of output and
new cell state gives new hidden state which is then given to
next cell of ERNN.
In ERNN, there are different gates input gate ,output gate, forget
gate and cell state. These gates determine which input is to keep
and which input is not important and need to discard. ERNN
takes input vector, previous cell state and previous hidden state
and apply different operations on it and gives output and cell
state. Different activation functions are used in ERNN like
Sigmoid and Tanh these functions help in maintaining cell
In this section results are discussed for experiment we use
dataset with attributes and techniques as mentioned above.
In the beginning dataset is loaded into system then data is
split into training and testing. MI is applied on it which give
values to features accordingly. While predicting load it gives
more importance to scheduled generation as compare to other
features. After that Features are given to DT which tells about
the importance of each feature accordingly. After which RFE is
applied on feature and most relevant three features are selected,
which are then given to classifier which training on those
feature an forecast results. Which are then compare to actual
results and performance metric are computed.
A. Dataset Description
In this proposed scheme data is taken from regional market
of National Electricity Market (NEM), Australia [
]. This
dataset is of a grid in New South Wales (NSW) region. NEM
dataset has many attributes from which six attributes time,
dispatch price or spot price, scheduled demand, scheduled
generation, semi scheduled generation and net import are used.
The data has the attributes: dispatch price ($/MWh), scheduled
demand (Wh), scheduled generation (MW), semi scheduled
generation (MW) and net import (MW). NEM dataset has data
of 2 days from 15 October 2018 21:00 to 17 October 2018
20:55 of NSW region in Australia. This dataset is of 5 min
intervals which has total of 576 instances. Data is split into
two parts. 75% training data is used for training and 25% is
used for testing. This means that 36 hours data is used for
training and 12 hours data is for prediction. Data is split in
same way for both load and price prediction.
B. Data Preprocessing
In data preprocessing data is loaded into system and
unnecessary columns are removed. Then data is normalize and
Data Set
Recursive Feature
2 Stage Feature
Decision Tree
Recurrent Neural Network
Predicted Load
And Price
Conditional Mutual
Fig. 1: System Model
decimal values are converted into integers. Mutual formation
is then applied to data. MI then give importance to features
according to their correlation as shown in Fig. 2 and Fig. 3.
After which these values are given to decision tree which gives
best features from dataset as shown in Fig. 2 and Fig. 3. RFE
is then applied to feature to removes redundancy from features.
C. Load Forecasting
Selected features are then given to classifier which forecast
load. Here in load forecasting, we have also compare FFNN
and RNN techniques with ERNN. Which shows that ERNN
gives better result then remaining two techniques. Results are
given in Fig. 4 and Fig. 5. These graphs show forecasting of
load for 12 hour ahead and 1 hour ahead, respectively.
D. Price Forecasting
In price forecasting we have same steps of feature selection
and feature extraction after which features are given to same
forecasting engine as given to load forecasting made by
classifier is given in Fig. 6 and Fig. 7. In Fig. 6, twelve hours
TABLE I: Load Forecasting Performance Evaluators
ERNN 11.7 29.15 34.26 8.89
RNN 64.48 77.65 80.30 9.10
FFNN 113.84 149.91 150.89 14.22
TABLE II: Price Forecasting Performance Evaluators
ERNN 9.68 17.44 31.11 44.97
RNN 19.28 17.29 31.05 40.54
FFNN 27.00 21.45 36.74 45.08
of prediction is made after training of 36 hours from Fig. 6 it is
clear that performance of FFNN is not that much good. RNN
and ERNN is giving good prediction. In Fig. 7, one hour of
price forecasting is shown. One hour of forecasting shows that
ERNN shows better prediction then RNN and FFNN. These
graph shows that our proposed scheme performs better then
benchmark techniques.
Dispatch Price (
Scheduled Generation (MW)
Semi Scheduled Generation (MW)
Net Import (MW)
Fig. 2: MI and DT feature importance for load
Scheduled Demand (MW)
Scheduled Generation (MW)
Semi Scheduled Generation (MW)
Net Import (MW)
Fig. 3: MI and DT feature importance for price
E. Performance Evaluation
To Evaluate the performance, four evaluator are used:
Root Mean Square Error (RMSE), Mean Average Percentage
Error(MAPE), Mean Square Error(MSE) and Mean Absolute
20 40 60 80 100 120 140
5 Minutes Interval
Load (MW)
Fig. 4: Load Forecasting Comparison of 12 Hours
2 4 6 8 10
5 Minutes Interval
Load (MW)
Fig. 5: Hour Ahead Load Forecasting Comparison
Error (MAE). MAPE has the lowest value in load forecasting;
however, in price forecasting MAPE has high values as shown
in Table I and Table II and its graphical presentation is shown
in Fig. 8 and Fig. 9.
20 40 60 80 100 120 140
5 Minutes Interval
Price ($/MWh)
Fig. 6: Price Forecasting Comparison of 12 Hours
2 4 6 8 10
5 Minutes Interval
Price ($/MWh)
Fig. 7: Hour Ahead Price Forecasting Comparison
Error Value
Fig. 8: Load Forecasting Error Comparison
Error Value
Fig. 9: Price Forecasting Error Comparison
An efficient technique is proposed to forecast load and price
of electricity using data analytics. Enhanced RNN is proposed
in this paper for short term price and load forecasting. The
proposed model consists of data preprocessing. It is done by
eliminating irrelevant features using RFE and DTC. It reduces
redundancy by MI. The proposed model trains and tests data
using LSTM. Experimental results prove the effectiveness of
proposed scheme. Performance results show that our proposed
scheme has less MAPE as compared to FFNN and RNN. NEM
data set is used for training and testing of data for forecasting.
Y. Zhang, T. Huang, and E. F. Bompard, “Big data analytics in smart
grids: a review,” Energy Informatics, vol. 1, no. 1, p. 8, 2018.
J.-B. Fiot and F. Dinuzzo, “Electricity demand forecasting by multi-task
learning,” IEEE Transactions on Smart Grid, vol. 9, no. 2, pp. 544–551,
H. Shi, M. Xu, and R. Li, “Deep learning for household load forecast-
ing—a novel pooling deep rnn, IEEE Transactions on Smart Grid, vol. 9,
no. 5, pp. 5271–5280, 2018.
B. Stephen, X. Tang, P. R. Harvey, S. Galloway, and K. I. Jennett,
“Incorporating practice theory in sub-profile models for short term
aggregated residential load forecasting,” IEEE Transactions on Smart
Grid, vol. 8, no. 4, pp. 1591–1598, 2017.
S. ZAKARYA, H. ABBAS, and M. BELAL, “Long-term deep learning
load forecasting based on social and economic factors in the kuwait
region.” Journal of Theoretical & Applied Information Technology,
vol. 95, no. 7, 2017.
A. Tajer, “Load forecasting via diversified state prediction in multi-area
power networks, IEEE Transactions on Smart Grid, vol. 8, no. 6, pp.
2675–2684, 2017.
P. Vrablecov
a, A. B. Ezzeddine, V. Rozinajov
a, S.
arik, and A. K.
Sangaiah, “Smart grid load forecasting using online support vector
regression,” Computers & Electrical Engineering, vol. 65, pp. 102–117,
P. Lusis, K. R. Khalilpour, L. Andrew, and A. Liebman, “Short-term
residential load forecasting: Impact of calendar effects and forecast
granularity, Applied Energy, vol. 205, pp. 654–669, 2017.
C. Tong, J. Li, C. Lang, F. Kong, J. Niu, and J. J. Rodrigues, “An
efficient deep model for day-ahead electricity load forecasting with
stacked denoising auto-encoders,” Journal of Parallel and Distributed
Computing, vol. 117, pp. 267–273, 2018.
H. Jiang, Y. Zhang, E. Muljadi, J. J. Zhang, and D. W. Gao, “A short-term
and high-resolution distribution system load forecasting approach using
support vector regression with hybrid parameters optimization, IEEE
Transactions on Smart Grid, vol. 9, no. 4, pp. 3341–3350, 2018.
M. Rafiei, T. Niknam, J. Aghaei, M. Shafie-khah, and J. P. Catal
“Probabilistic load forecasting using an improved wavelet neural network
trained by generalized extreme learning machine,” IEEE Transactions
on Smart Grid, 2018.
National electricity market australian energy market operator. Australia.
[Online]. Available:
... The use of Recurrent Neural Networks (RNNs) models has expanded to several areas and applications, such as: pattern recognition [1]; prediction in mMIMO for enhanced performance in wireless communications [2]; trajectory tracking on soft continuum robots [3]; control for quadrotor attitude and altitude [4]; Data Analytics for Short Term Price and Load Forecasting in Smart Grids [5];, fault accommodation control for a biped robot [6];, discretizing time series [7]; table field extraction in business documents [8]; Lung cancer detection [9]; and recognition of English handwritten text [10], among others. ...
... 4. Systems Identification [29] and [30]. 5. Modeling [31,32,33,34] and [35]. ...
... The evaluation metric is usually the Mean Squared Error (MSE), presented in equation (5).: ...
... Usman et al. [13] presented a DL based algorithm to forecast price and demand on big data utilizing deeper long short term memory (LSTM). Because of adaptive and automated feature learning of DNN, process of big data has simpler with LSTM as related to completely data driven techniques. ...
Full-text available
Recent economic growth and development have considerably raised energy consumption over the globe. Electric load prediction approaches become essential for effective planning, decision-making, and contract evaluation of the power systems. In order to achieve effective forecasting outcomes with minimum computation time, this study develops an improved whale optimization with deep learning enabled load prediction (IWO-DLELP) scheme for energy storage systems (ESS) in smart grid platform. The major intention of the IWO-DLELP technique is to effectually forecast the electric load in SG environment for designing proficient ESS. The proposed IWO-DLELP model initially undergoes pre-processing in two stages namely min-max normaliza-tion and feature selection. Besides, partition clustering approach is applied for the decomposition of data into distinct clusters with respect to distance and objective functions. Moreover, IWO with bidirectional gated recurrent unit (BiGRU) model is applied for the prediction of load and the hyperparameters are tuned by the use of IWO algorithm. The experiment analysis reported the enhanced results of the IWO-DLELP model over the recent methods interms of distinct evaluation measures.
... The cell memory is represented in equation 2 [56]: Ct = (Ft ⊗ Ct-1) ⊕ (It ⊗ tanh(WcXt +UcHt-1 + Bc)) (2) Where C is the cell memory, H is the hidden state, X is the input, B is bias, W and U represent the weight vectors of F and H, respectively, tanh represents the tangent function. The short-term load and price forecasting can be achieved by enhanced RNN that eliminates irrelevant features by using recursive feature elimination [57]. The battery is an important component of any SG. ...
... The cell memory is represented in equation 2 [56]: Ct = (Ft ⊗ Ct-1) ⊕ (It ⊗ tanh(WcXt +UcHt-1 + Bc)) (2) Where C is the cell memory, H is the hidden state, X is the input, B is bias, W and U represent the weight vectors of F and H, respectively, tanh represents the tangent function. The short-term load and price forecasting can be achieved by enhanced RNN that eliminates irrelevant features by using recursive feature elimination [57]. The battery is an important component of any SG. ...
Full-text available
The manuscript represents the state-of-the-art review of the deep learning methods for smart grid applications. This paper reviews novel applications of deep learning algorithms in smart grid. The deep learning based three algorithms i.e., Long-Short Term Memory, recurrent neural network, convolution neural network found to be most useful in smart grid application. These algorithms are found to be most useful for forecasting, cyber-attack, anomaly detection and electricity theft in smart grid. This paper briefly surveys the most usable deep learning algorithms for making the smart is resilience, accurate, and safe. The review result shows that the mentioned deep learning algorithms give an excellent results over other deep learning algorithm. Therefore, these three algorithms are widely acceptable for the evaluation of smart grids.
... The combination of the cluster forecast provided a more precise prediction while keeping the information's variability. Usman et al. [15] proposed a modified RNN for short-term pricing and predictive modelling to forecast electricity load and price using data analytics. Data preprocessing techniques such as RFE and DTC are used to eliminate extraneous characteristics to decreases redundancy. ...
Full-text available
Smart grids provide a unique platform to the participants of energy markets to tweak their offerings based on demand-side management. Responding quickly to the needs of the market can help to improve the reliability of the system, as well as the cost of capital investments. Electric load forecasting is important because it is used to make and run decisions about the power grid. However, people use electricity in nonlinear ways, which makes the electric load profile a complicated signal. Even though there has been a lot of research done in this field, an accurate forecasting model is still needed. In this regard, this article proposed a hybrid cross-channel-communication (C3)-enabled CNN-LSTM model for accurate load forecasting which helps decision making in smart grids. The proposed model is the combination of three different models, i.e., a C3 block to enable channel communication of a CNN (convolutional neural networks) model, two convolutional layers to extract the features and an LSTM (long short-term memory network) model for forecasting. In the proposed hybrid model, Leaky ReLu (rectified linear unit) was used as activation function instead of sigmoid. The channel communication in CNN model makes the proposed model very light and efficient. Extensive experimentation was done on electricity load data. The results show the model’s high efficiency. The proposed model shows 98.3% accuracy and 0.4560 MAPE error.
Smart Grid (SG) has smart instruments which can communicate using Advanced Metering Infrastructure (AMI). This will require SG a large storage space for storing the time-series data. The veracity of data increases with respect to time and becomes a challenging task for data managers. For managing large data sets, preprocessing is a fundamental part of the data management system, and often it is called Intelligent Compression (IC). IC is a method for removing redundant or repeated data from a disk or any other storage device. In this paper, various filtering techniques are used to compress and preprocess large data set of power consumption in SG. Filtering eliminates abnormal or unwanted components, signals, or features from a data set. Here, five filtering techniques have been used as Butterworth, Smoothing, Kalman, Frequency swept, and Filtfilt with Long Short-Term Memory (LSTM) to predict Power Consumption in the Smart Grid. The results are compared with different evaluation metrics for five different datasets. It is found that Filtfilt filtering techniques with LSTM provide better performance and accuracy over other filtering techniques.
Full-text available
Price forecasting (PF) is the primary concern in distributed power generation. This paper presents a novel and improved technique to forecast electricity prices. The data of various power producers, Capacity Purchase Price (CPP), Power Purchase Price (PPP), Tariff rates, and load demand from National Electric Power Regulatory Authority (NEPRA) are considered for MAPE reduction in PF. Eight time-series and auto-regression algorithms are developed for data fetching and setting the objective function. The feed-forward ANFIS based on the ML approach and space vector regression (SVR) is introduced to PF by taking the input from time series and auto-regression (AR) algorithms. Best-feature selection is conducted by adopting the Binary Genetic Algorithm (BGA)-Principal Component Analysis (PCA) approach that ultimately minimizes the complexity and computational time of the model. The proposed integration strategy computes the mean absolute percentage error (MAPE), and the overall improvement percentage is 9.24%, which is valuable in price forecasting of the energy management system (EMS). In the end, EMS based on the Firefly algorithm (FA) has been presented, and by implementing FA, the cost of electricity has been reduced by 21%, 19%, and 20% for building 1, 2, and 3, respectively.
Full-text available
Abstract Data analytics are now playing a more important role in the modern industrial systems. Driven by the development of information and communication technology, an information layer is now added to the conventional electricity transmission and distribution network for data collection, storage and analysis with the help of wide installation of smart meters and sensors. This paper introduces the big data analytics and corresponding applications in smart grids. The characterizations of big data, smart grids as well as huge amount of data collection are firstly discussed as a prelude to illustrating the motivation and potential advantages of implementing advanced data analytics in smart grids. Basic concepts and the procedures of the typical data analytics for general problems are also discussed. The advanced applications of different data analytics in smart grids are addressed as the main part of this paper. By dealing with huge amount of data from electricity network, meteorological information system, geographical information system etc., many benefits can be brought to the existing power system and improve the customer service as well as the social welfare in the era of big data. However, to advance the applications of the big data analytics in real smart grids, many issues such as techniques, awareness, synergies, etc., have to be overcome.
Full-text available
We explore the application of kernel-based multi-task learning techniques to forecast the demand of electricity in multiple nodes of a distribution network. We show that recently developed output kernel learning techniques are particularly well suited to solve this problem, as they allow to flexibly model the complex seasonal effects that characterize electricity demand data, while learning and exploiting correlations between multiple demand profiles. We also demonstrate that kernels with a multiplicative structure yield superior predictive performance with respect to the widely adopted (generalized) additive models. Our study is based on residential and industrial smart meter data provided by the Irish Commission for Energy Regulation (CER).
Competitive transactions resulting from recent restructuring of the electricity market, have made achieving a precise and reliable load forecasting, especially probabilistic load forecasting, an important topic. Hence, this paper presents a novel hybrid method of probabilistic electricity load forecasting, including generalized extreme learning machine (GELM) for training an improved wavelet neural network (IWNN), wavelet preprocessing and bootstrapping. In the proposed method, the forecasting model and data noise uncertainties are taken into account while the output of the model is the load probabilistic interval. In order to validate the method, it is implemented on the Ontario and Australian electricity markets data. Also, in order to remove the influence of model parameters and data on performance validation, Friedman and post-hoc tests, which are non-parametric tests, are applied to the proposed method. The results demonstrate the high performance, accuracy and reliability of the proposed method.
Load forecasting (LF) is a technique used by energy-providing companies to predict the power needed. LF is of great importance for ensuring sufficient capacity and manipulating the deregulation of the power industry in many countries, such as Arab gulf countries. Moreover, reduction of load forecasting error leads to lower costs and could save billions of dollars. Recently, further improvement has been introduced using more complex models that take into account dependencies among hidden layers. Also, many approach based model are presented, but all of them have limitations prediction capabilities. The purpose of this work is to demonstrate the load forecasting classes and factors impacting its performance, especially in Kuwaiti region in Arab Gulf. This work presents a novel deep leaning model that involves generating more accurate predictions for the electric load based on hierarchal learning architecture. It is integrates the features of data in discovering most influent factors affecting electrical load usage. The dataset used is the actual data from Ministry of Electrical in Kuwait, the data for load is in mega-watt long-term for the years 2006 to year 2015, which is trained using ARIMA and neural networks models. The load forecasting is done for the year 2016 and is validated for the accuracy and less for error rate. Results indicate that this architecture performs quite well when compared to traditional approaches and deep neural network.
Literature is rich in methodologies for “aggregated” load forecasting which has helped electricity network operators and retailers in optimal planning and scheduling. The recent increase in the uptake of distributed generation and storage systems has generated new demand for “disaggregated” load forecasting for a single-customer or even down at an appliance level. Access to high resolution data from smart meters has enabled the research community to assess conventional load forecasting techniques and develop new forecasting strategies suitable for demand-side disaggregated loads. This paper studies how calendar effects, forecasting granularity and the length of the training set affect the accuracy of a day-ahead load forecast for residential customers. Root mean square error (RMSE) and normalized RMSE were used as forecast error metrics. Regression trees, neural networks, and support vector regression yielded similar average RMSE results, but statistical analysis showed that regression trees technique is significantly better. The use of historical load profiles with daily and weekly seasonality, combined with weather data, leaves the explicit calendar effects a very low predictive power. In the setting studied here, it was shown that forecast errors can be reduced by using a coarser forecast granularity. It was also found that one year of historical data is sufficient to develop a load forecast model for residential customers as a further increase in training dataset has a marginal benefit.
Smart grid, an integral part of a smart city, provides new opportunities for efficient energy management, possibly leading to big cost savings and a great contribution to the environment. Grid innovations and liberalization of the electricity market have significantly changed the character of data analysis in power engineering. Online processing of large amounts of data continuously generated by the smart grid can deliver timely and precise power load forecasts – an important input for interactions on the market where the energy can be contracted even minutes ahead of its consumption to minimize the grid imbalances. We demonstrate the suitability of online support vector regression (SVR) method to short term power load forecasting and thoroughly explore its pros and cons. We present a comparison of ten state-of-the-art forecasting methods in terms of accuracy on public Irish CER dataset. Online SVR achieved accuracy of complex tree-based ensemble methods and advanced online methods.
In real word it is quite meaningful to forecast the day-ahead electricity load for an area, which is beneficial to reduction of electricity waste and rational arrangement of electric generator units. The deployment of various sensors strongly pushes this forecasting research into a "big data" era for a huge amount of information has been accumulated. Meanwhile the prosperous development of deep learning (DL) theory provides powerful tools to handle massive data and often outperforms conventional machine learning methods in many traditional fields. Inspired by these, we propose a deep learning based model which firstly refines features by stacked denoising auto-encoders (SDAs) from history electricity load data and related temperature parameters, subsequently trains a support vector regression (SVR) model to forecast the day-ahead total electricity load. The most significant contribution of this heterogeneous deep model is that the abstract features extracted by SADs from original electricity load data are proven to describe and forecast the load tendency more accurately with lower errors. We evaluate this proposed model by comparing with plain SVR and artificial neural networks (ANNs) models, and the experimental results validate its performance improvements.
The key challenge for household load forecasting lies in the high volatility and uncertainty of load profiles. Traditional methods tend to avoid such uncertainty by load aggregation (to offset uncertainties), customer classification (to cluster uncertainties) and spectral analysis (to filter out uncertainties). This paper, for the first time, aims to directly learn the uncertainty by applying a new breed of machine learning algorithms – deep learning. However simply adding layers in neural networks will cap the forecasting performance due to the occurrence of overfitting. A novel pooling-based deep recurrent neural network (PDRNN) is proposed in this paper which batches a group of customers’ load profiles into a pool of inputs. Essentially the model could address the over-fitting issue by increasing data diversity and volume. This work reports the first attempts to develop a bespoke deep learning application for household load forecasting and achieved preliminary success. The developed method is implemented on Tensorflow deep learning platform and tested on 920 smart metered customers from Ireland. Compared with the state-of-art techniques in household load forecasting, the proposed method outperforms ARIMA by 19.5%, SVR by 13.1% and classical deep RNN by 6.5% in terms of RMSE.
This paper proposes an approach for distribution system load forecasting, which aims to provide highly accurate short-term load forecasting with high resolution utilizing a support vector regression (SVR) based forecaster and a two-step hybrid parameters optimization method. Specifically, because the load profiles in distribution systems contain abrupt deviations, a data normalization is designed as the pretreatment for the collected historical load data. Then an SVR model is trained by the load data to forecast the future load. For better performance of SVR, a two-step hybrid optimization algorithm is proposed to determine the best parameters. In the first step of the hybrid optimization algorithm, a designed grid traverse algorithm (GTA) is used to narrow the parameters searching area from a global to local space. In the second step, based on the result of the GTA, particle swarm optimization (PSO) is used to determine the best parameters in the local parameter space. After the best parameters are determined, the SVR model is used to forecast the short-term load deviation in the distribution system. The performance of the proposed approach is compared to some classic methods in later sections of the paper.
Load forecasting has a pivotal role in operating electric utilities. This paper proposes a learning-based tool for short-term load forecasting via first predicting the state parameters of the grid and then delineating load forecasts as functions of the predicted state parameters. Such indirect load forecasting via predicting state parameters leads to improved forecast quality due to the inherent diversity in predictions for state parameters. Specifically, due to the strong inter-connectivity among network components, some state parameters are shared by multiple substations. Hence, allowing each substation to provide local predictions for its associated state parameters based on its local dynamics enables providing multiple predictions for each shared state parameter, leading to a diversified set of predictions for it. Our analysis shows that the proposed aggregation framework provides a prediction for each state parameter such that the quality of this prediction equals to that of the best local prediction provided for that state parameter. This implies that this framework can identify and track the best local prediction for each state parameter without requiring any knowledge about network dynamics.