Professional Documents
Culture Documents
Artificial Neural Network Based Hydro Electric Generation Modelling
Artificial Neural Network Based Hydro Electric Generation Modelling
Volume 2, No 1, 2010
© Copyright 2010 All rights reserved Integrated Publishing Association
Artificial Neural Network based Hydro Electric Generation Modelling
Deepika Yadav., Naresh.R, Veena Sharma
Electrical Engineering Department, National Institute of Technology, Hamirpur, HP
deepikayadav2008@gmail.com
ABSTRACT
Hydropower generation is a function of discharge of the generating units and the difference
between the fore bay and tailrace levels of the reservoir, and is subject to penstock head
losses and to the generation unit efficiency factor, which in turn is a function of the reservoir
level and reservoir capacity. For this actual plant data from Sewa Hydroelectric Project
StageII which is a runofthe river project having installed capacity of 120 MW situated in
Jammu region has been used.In this paper two hydro electric models such as reservoir level
versus capacity model and head loss versus water discharge rate have been studied which are
used for calculating net head and further can be used for online implementation of
Availability Based Tariff in which day ahead scheduling is done. In order to accomplish this
task, data from plant is employed for training, validating and testing the artificial neural
network (ANN) model which provide accurate results. Thereafter with these models, a
comparison is made with multiple regression models in terms of their prediction accuracy,
mean square error and regression R value.
Keywords: Artificial neural network, ANOVA analysis, LevenbergMarquardt algorithm,
hydroelectric generation models
1. Introduction
In hydro electric Power plants, for calculating energy and online implementation of
availability based tariff in Indian power industry [Bhushan. 2005; Christensen et al. 1988;
Geetha et al. 2008; and Deshmukh et al. 2008], there is always a need to develop models for
hydro electric plant as each one is unique to its location and requirement. In most cases, the
parameters to be estimated are of nonlinear model with respect to control and state variables.
Here data used has been taken from Sewa Hydroelectric Project StageII, a runofthe river
project, which fulfills the partial requirements of the irrigation in state of Jammu and
Kashmir. The power house is located in a village called Mashka near the junction of Sewa
and Ravi, The project will generate 533.52 million units in a 90% dependable year and also
provide 120 MW peaking capacity in the power system of northern region. This plant has a
small reservoir with maximum storage capacity of 0.9174 million cubic meters (MCM) and
average storage capacity of 0.2234 MCM. Moreover, elevation is taken from above mean sea
level through some level sensors, maximum reservoir level of this plant is 1200 meter and
average reservoir level measured is 1184 meter.The project envisages 53 meterhigh concrete
gravity dam, a 10,020 meterlong head race tunnel and its power house will be equipped with
3*40MW vertical Pelton turbine units with rated net head of 560m. Its geographical
coordinates having latitude 32 ° 36’ 38” N to 32° 41’ 00” N and longitude 75° 48’ 46” E to
75° 55’ 38” E is shown in figure 1, referred from site (www.nhpcindia.com)
Hydroelectric scheduling of the plants requires a judicious modeling of each of the hydro
electric plant for an improved efficiency, optimum use of water resources and to arrest
56
INTERNATIONAL JOURNAL OF APPLIED ENGINEERING RESEARCH, DINDIGUL
Volume 2, No 1, 2010
© Copyright 2010 All rights reserved Integrated Publishing Association
possible losses. The scheduling of water releases, which is the water discharge for some
period of time, depends on reservoir capacities [Wood and Wollenberg, 1984]. Since hydro
electric power generation is dependent on the discharge, an optimal discharge schedule is
paramount for an optimal hydro electric generation scheduling. Scheduling and modeling of
water releases is an integral part which plays a very important role in day to day operations of
a power system.
In this paper, we used the neural network model [Buizza et al. 2002; Senjyu et al. 2002;
Randall et al. 2002; Subramanian et al. 1999; Myers et al. 1993 and Fauset. 1994] which is a
flexible mathematical structure that is capable of identifying complex nonlinear relationships
between input and
Figure 1: Location Map
output data sets taken from Sewa Hydroelectric Project StageII. Once the neural network
model is trained, it is capable to predict with accuracy depending upon the accuracy of the
training data provided. The ANN generated results are evaluated using mean square error and
regression R value in neural network fitting tool in MATLAB 7.5. Likewise, prediction is
also made by Analysis of Variance (ANOVA) approach in terms of Regression value and
standard error to predict best model. This paper is structured as follows. Section 2 presents
the Neural network overview using nftool employing LevenbergMarquardt algorithm.
Section 3, 4 describes the simulation of ANN and ANOVA results for reservoir level versus
capacity model and head loss versus water discharge rate respectively. Finally, Section 5
outlines the conclusions.
2. Neural Network Overview
Neural networks are inspired by nervous systems found in biological organisms. It is
comprised of data processing units (neurons) connected via adjustable connection weights.
57
INTERNATIONAL JOURNAL OF APPLIED ENGINEERING RESEARCH, DINDIGUL
Volume 2, No 1, 2010
© Copyright 2010 All rights reserved Integrated Publishing Association
Neurons are arranged in layers, an input layer, hidden layer(s), and an output layer. There is
no specific rule that dictates the number of hidden layers. The function is largely established
based on the connections between elements of the network. In the input layer each neuron is
designated to one of the input parameters. The network learns by applying a back
propagation algorithm which compares the neural network simulated output values to the
actual values and calculates a prediction error. The error is then back propagated through the
network and weights are adjusted as the network attempts to decrease the prediction error by
optimizing the weights that contribute most to the error. The training or learning of the
network occurs through the introduction of cycles of data patterns (epochs or iterations) to the
network. One problem with neural network training is the tendency for the network to
memorize the training data after an extended learning phase. If the network over learns the
training data it is more difficult for the network to generalize to a data set that was not seen
by the network during training. Therefore, it is common practice to divide the data set into a
learning data set that is used to train the network and a validation data set that is used to test
network performance. Figure 2 shows the representation of neural network diagram with
inputs ai, weights wi, hidden layer, and an output z
ˆ [Beale et al.1996]. In the present study,
neural network fitting tool (nftool) of MATLAB7.5 [Beale et al.1996] has been used.
Figure 2: Feedforward neural network model
This research employed supervised learning where the target values for the output are
presented to the network, in order for the network to update its weights. Supervised learning
attempts to match the output of the network to values that have already been defined. After
training network verification is applied in which only the input values are presented to the
network so that the success of the training can be established an algorithm that trains ANN 10
to 100 times faster than the usual back propagation algorithm is the LevenbergMarquardt
algorithm. While back propagation is a steepest descent algorithm, the LevenbergMarquardt
algorithm is a variation of Newton's method [Hagan et al. 1994]. In this paper, the
LevenbergMarquardt algorithm has been employed which is an approximation to Newton's
method. Suppose a function V (x), which we want to minimize with respect to the parameter
vector (x), then Newton's method would be
D ( x ) = -[ Ñ 2 V ( x )] -1 ÑV ( x ) (1)
58
INTERNATIONAL JOURNAL OF APPLIED ENGINEERING RESEARCH, DINDIGUL
Volume 2, No 1, 2010
© Copyright 2010 All rights reserved Integrated Publishing Association
and S(x) is given by
N
S ( x ) = å e i ( x ) Ñ 2 e i ( x ) (6)
i =1
Neglecting the secondorder derivatives of the error vector, i.e., assuming that S(X) » 0, the
Hessian matrix is given by
Ñ 2 V ( x ) = J T ( x ) J ( x ) (7)
and substituting (7) and (3) into (1) we obtain the GaussNewton update, given by
D x = -[ J T ( x ) J ( x )] - 1 J T ( x ) e ( x ) (8)
The advantage of GaussNewton over the standard Newton's method is that it does not
require calculation of secondorder derivatives. Nevertheless, the matrix J T (x) J(x) may not be
invertible. This is overcome with the LevenbergMarquardt algorithm, which consists in
finding the update given by
D x = - [ J T ( x ) J ( x ) + m I ] - 1 J T ( x ) e ( x ) (9)
When the scalar µ is very small or null, the LevenbergMarquardt algorithm becomes Gauss
Newton, which should provide faster convergence, while for higher µ values, when the first
term within brackets of (9) is negligible with respect to the second term within brackets, the
algorithm becomes steepest descent. Hence, the LevenbergMarquardt algorithm provides a
nice compromise between the speed of GaussNewton and the guaranteed convergence of
steepest descent [Hagan et al. 1994]. Here, performance function which is the sum of squared
errors between the target outputs and the network's simulated outputs (as is typical in training
feed forward networks) is proportional to µ.Thus, µ is decreased after each successful step
(reduction in performance function) and is increased only when a tentative step would
increase the performance function. In this way, the performance function is always reduced at
59
INTERNATIONAL JOURNAL OF APPLIED ENGINEERING RESEARCH, DINDIGUL
Volume 2, No 1, 2010
© Copyright 2010 All rights reserved Integrated Publishing Association
each iteration of the algorithm. This algorithm appears to be the fastest method for training
moderatesized feed forward neural networks.
3. Reservoir Level versus Capacity Model
The modeling of water stored in a reservoir forms a crucial part of any hydroelectric
operational study because it determines the gross head of each plant. This model relates the
elevation to the volume of water stored in the reservoir.
3.1 Modelling Using ANN
In this model of reservoir level (m) versus capacity (MCM), the actual river data using
‘nftool’ of MATLAB was used to train the neural network model. To use this tool, first
convert the data into MATLAB data file and provide as input to nftool. The system takes
60% of data for training, 20% for validation and 20% for testing, so that the same data will
not be used for testing. It requires many runs to converge or to get expected training. Once
the system was trained then it tests with remaining sample of data for testing. Figure 3 shows
the performance accuracy employing different numbers of hidden nodes.
Figure 3: Accuracy versus number of trials with different hidden neurons
Table 1: Performance evaluation of Training, Validation and Testing
60
INTERNATIONAL JOURNAL OF APPLIED ENGINEERING RESEARCH, DINDIGUL
Volume 2, No 1, 2010
© Copyright 2010 All rights reserved Integrated Publishing Association
where, ym = the observed dependent variable
ˆ m = the fitted dependent variable for the independent variable xm
y
y m
y = mean, y m = å
M
xm= the independent variable in the m th trial
M
M 2
2
å ( y m - y ) ˆ m ) represents residual
represents total sum of squares, while m å=1 ( y m - y
m =1
sum of squares
R Square is a measure of the explanatory power of the model. Here for best model chosen R
Square is 0.999939, 0.999902 and 0.988785 for training, validation and testing respectively
as shown in figure 4(a).
In figure 4 (a) the dashed line is the perfect fit line where outputs and targets are equal to
each other. The circles are the data points and coloured line represents the best fit between
outputs and targets. Here it is important to note that circles gather across the dashed line, so
our outputs are not far from targets. From the graph, it can be realized that the best hidden
unit with 99% accuracy is with 5 neurons with third trial for this model. Figure 4(b) depicts
the training, validation and test mean square errors for LevenbergMarquardt algorithm with
5 hidden neurons. The training stops when MSE do not change significantly. The comparison
of actual and predicted results by neural network model for reservoir level versus reservoir
61
INTERNATIONAL JOURNAL OF APPLIED ENGINEERING RESEARCH, DINDIGUL
Volume 2, No 1, 2010
© Copyright 2010 All rights reserved Integrated Publishing Association
capacity model has been shown in figure 5(a) which clearly reveals that neural network
model has tracked the experimental data closely. Error plot between actual and predicted
results by neural network model has been shown in figure 5(b), which is within quite
acceptable limits.
Figure 4 (a): Regression plots for actual and predicted results by feedforward neural
network model for training, validation, testing samples and all data set (b): shows training,
validation and testing mean square errors for LevenbergMarquardt algorithm with 5 neurons.
62
INTERNATIONAL JOURNAL OF APPLIED ENGINEERING RESEARCH, DINDIGUL
Volume 2, No 1, 2010
© Copyright 2010 All rights reserved Integrated Publishing Association
Figure 5 (a): Plot of actual and predicted results for Reservoir level versus Capacity model
using LevenbergMarquardt algorithm (b): shows Error Plot between Actual and Predicted
Results by neural network model
63
INTERNATIONAL JOURNAL OF APPLIED ENGINEERING RESEARCH, DINDIGUL
Volume 2, No 1, 2010
© Copyright 2010 All rights reserved Integrated Publishing Association
3.2 Modelling Using ANOVA
Analysis of variance [Draper et al. 1998 and Myers et al. 1993] is a parametric procedure
Figure 6: ANOVA results obtained for Reservoir level versus Capacity
64
INTERNATIONAL JOURNAL OF APPLIED ENGINEERING RESEARCH, DINDIGUL
Volume 2, No 1, 2010
© Copyright 2010 All rights reserved Integrated Publishing Association
Figure 7: Plot for R Value, Standard error and Accuracy
The graphical curves of fit obtained are shown in figure 6(a). In figure 6(b) the residuals
using ANOVA model for different polynomials have been plotted. From the analysis of the
above graphical results it is evident that the higher order polynomial provides better fit in this
case. Further analysis to regression R Value, Standard error and Accuracy has been plotted in
figure 7 for different degrees of polynomials. The details of ANOVA analysis approach can
be referred in [Naresh et al. 2009].
4. Head Loss versus Water Discharge Rate Model
When determining head (falling water), gross or static head and net or dynamic head must be
considered. Gross head is the vertical distance between the top of the penstock and the point
where the water hits the turbine. Net head is gross head minus the pressure or head losses due
to friction and turbulence in the penstock. These head losses depend on the type, diameter,
and length of the penstock piping, and the number of bends or elbows. Gross head can be
used to estimate power availability and determine general feasibility, but net head is used to
calculate the actual power available. In addition, electricity demand and generation
scheduling depend on water released during the next day through generators and/or gates.
The amount is determined by the water level of the reservoir of the preceding day and the
water arriving from runoff. Here in this section the head loss (m) versus water discharge rate
(m 3 s 1 ) model analysis has been outlined.
4.1 Modelling Using ANN
To evaluate neural network performance, initialization of connection weights, training,
validation and testing has been performed with five independent random trials for weight
initialization as listed in table 2. Figure 8 shows the performance plot employing different
65
INTERNATIONAL JOURNAL OF APPLIED ENGINEERING RESEARCH, DINDIGUL
Volume 2, No 1, 2010
© Copyright 2010 All rights reserved Integrated Publishing Association
numbers of hidden units. It can be noted from the graph that with increase in number of
neurons in the hidden layer, accuracy also increases. From the graph, it can be realized that
the best hidden unit with good accuracy is achieved with 5 neurons units on third trial.
Figure 8: Accuracy versus number of trials with different hidden neurons
Table 2: Performance evaluation of Training, Validation and Testing
66
INTERNATIONAL JOURNAL OF APPLIED ENGINEERING RESEARCH, DINDIGUL
Volume 2, No 1, 2010
© Copyright 2010 All rights reserved Integrated Publishing Association
In this network, training is provided for 100 epochs, minimum MSE for best model in case of
training is 2.41E08 as shown in figure 9 (b). The training stops when MSE do not change
significantly.Validation vectors are used to stop training early if the network performance on
the validation vectors fails to improve or remains the same for max fail epochs in a row, for
this model in MSE noted for validation is 3.01E03 as in figure 9(b).Test vectors are used as
a further check that the network is generalizing well, but do not have any effect on training
Neural Network Toolbox, minimum MSE for this model in case of testing is 2.14E03 as
shown in figure 9(b). Here for best model chosen R Square is 0.999999, 0.999997 and
0.999997 for training, validation and testing as shown in figure 9 (b). As per the model 99%
of variation in dependent variable has been explained by independent variable.
Figure 9 (a): Regression plots for actual and predicted results by feedforward neural
network model for training, validation, testing samples and all data set (b): shows training,
validation and testing mean square errors for LevenbergMarquardt algorithm with 5 neurons.
67
INTERNATIONAL JOURNAL OF APPLIED ENGINEERING RESEARCH, DINDIGUL
Volume 2, No 1, 2010
© Copyright 2010 All rights reserved Integrated Publishing Association
Figure 10 (a): Plot of actual and predicted results for head loss versus water discharge rate
model using LevenbergMarquardt algorithm Figure 10 (b): Error plot between actual and
predicted results by NN Model
68
INTERNATIONAL JOURNAL OF APPLIED ENGINEERING RESEARCH, DINDIGUL
Volume 2, No 1, 2010
© Copyright 2010 All rights reserved Integrated Publishing Association
The comparison between actual and predicted results by neural network model is shown
above in figure 10 (a). From figure 10 (b) it can be seen that small amount of errors are
present in the beginning of the predicted results and afterwards the neural network model is
predicting quite well.
4.2 Modelling Using ANOVA
Figure 11: ANOVA results obtained for head loss versus water discharge rate
It can be noted from figure 11(a) that although difference between the cubic,4 th ,5 th and 6 th
degree Polynomials were small and predicted data gets converged with the actual data for all.
The best fitting was obtained for 3 rd order model with 99.9893% accuracy with minimum
standard error obtained among all as shown in figure 12. Also, this model provides good
69
INTERNATIONAL JOURNAL OF APPLIED ENGINEERING RESEARCH, DINDIGUL
Volume 2, No 1, 2010
© Copyright 2010 All rights reserved Integrated Publishing Association
significant fit with regression R value 0.99. More details regarding this model can be found in
[Naresh et al. 2009].
Figure 12: Plot for R Value, Standard error and Accuracy
5. Conclusion
In this paper two hydro electric models, reservoir level versus capacity model and head loss
versus water discharge rate model have been developed using artificial neural network.
During modelling process 60% of the available data is used for training, 20% is used for
cross validation and 20% is used for testing. The data for each class are chosen randomly
from the data set. Further, the developed models are compared with ANOVA approach.
Predicted results by ANN and ANOVA analysis are quite cohesive to the actual results of
Sewa river. However, ANN proved to be a useful tool to predict and estimate nonlinear
relationship between the variables because of its adaptive capability. These models in a way
help in effective utilization of available water that can help us to fight against uncertainty,
especially for the optimal generation, scheduling of the runof river project in a multipurpose
context and also can be used as an effective input to the decision support system for realtime
operation of reservoir systems that results in increased power production and enhanced
revenue earnings in the process of planning and management of a water resources project.
70
INTERNATIONAL JOURNAL OF APPLIED ENGINEERING RESEARCH, DINDIGUL
Volume 2, No 1, 2010
© Copyright 2010 All rights reserved Integrated Publishing Association
6. Acknowledgment
The authors are grateful for the kind support rendered by the Electronics division of BHEL
Bangalore, India for carrying out this work.
7. References
2. Bhushan et al., 2004: The Indian medicine, In IEEE Power Engineering Society
General Meeting, Vol.2, pp.2336 – 2339.
3. Buizza and Taylor, 2002: Neural network load forecasting with weather ensemble
predictions. In Proceedings of IEEE Trans. on Power Systems, 17(3), pp.626632.
4. Christensen and Soliman, 1988: Optimization of the production of hydroelectric
power systems with a variable head. In Journal of Optimization Theory and
Applications, Springer Netherlands, 58(2), pp.301317.
6. Draper and Smith, 1998: Applied Regression Analysis, 3rd edition John Wiley &
Sons, New York.
7. Fauset, 1994: Fundamentals of Neural Networks, 3rd edition, PrenticeHall
International, New York.
8. Senjyu et al., 2002: Onehourahead load forecasting using neural network, IEEE
Trans. on Power Systems, 17(1), pp.113118.
9. Geetha and Jayashankar, 2008: Generation Dispatch with Storage and Renewables
under Availability Based Tariff. In Proceedings of TENCON 2008, IEEE Region 10
Conference, pp.16.
10. Hagan and Menhaj, 1994: Training feed forward networks with the Marquardt
algorithm. IEEE Trans. on Neural Networks, 5(6), pp.989993.
11. Subramanian et al., 1999: Reservoir Inflow Forecasting Using Neural Networks. In
Proceedings of the American Power Conference, Chicago, US, 61(1), pp.220226.
12. Myers and Walpole, 1993: Probability and Statistics for Engineers and Scientist, 5th
edition, Mac Millan Publishing Company, New York.
71
INTERNATIONAL JOURNAL OF APPLIED ENGINEERING RESEARCH, DINDIGUL
Volume 2, No 1, 2010
© Copyright 2010 All rights reserved Integrated Publishing Association
13. Naresh et al., 2009: Hydro Electric Generation Models for Hydro Power Station
Studies. In Proceedings of National ConferenceTACT09, NITHamirpur, India, 16
17 March 2009, pp.261264, ISBN:9789380043104.
14. Randall and Tagliarini, 2002: Using feed forward neural networks to model the effect
of precipitation on the water levels of the Northeast Cape Fear River. In Proceedings
of the IEEE Southeast Conference, Columbia, US, pp.338342.
15. Wood and Wollenberg, 1984: Power Generation, Operation, and Control, 2nd edition,
John Wiley & Sons, New York.
72