Final 5h5n6r

IMPLEMENTATION OF SHORT-TERM LOAD FORECASTING USING NEURAL NETWORKS AND ANFIS

By

P.Uday Kiran

M.Ajay Kumar

4/4 B.Tech(EEE)

M.Suresh

What is Load Forecasting?  Predicting the load

 It is important for maintaining the Power Plant  Forecaster ascertains the estimated load for required hour

Importance of Load Forecasting • Load Forecasting has always been the essential part of an efficient Power System planning and operation • Several Electric Power companies are now forecasting load power based on conventional methods • However, since the relationship between load power and factors influencing the load power is non-linear, it is difficult to identify its non-linearity by using conventional methods

Types of Load Forecasting  Short-Term Load Forecasting Load prediction period may be a week or shorter period than a week

 Medium –Term Load Forecasting Load prediction period may be few months  Long-Term Load Forecasting Load prediction period may be more than a year

Factors affecting the load Forecasting • • • • • • •

Seasonal changes Daily changes Temperature Humidity Clouds Random event Any economical or environmental change

Need for Forecasting the load • • • •

Planning of power generation Scheduling of fuel supplies and maintenance For minimizing the operation costs Important for supplier: With the forecasted load number of generations in operation can be controlled

Artificial Neural Network • A Neural network is a massively parallel-distributed processor made up of simple processing units, know as neurons. • It resembles brain in two aspects: 1.Knowledge is acquired by the network from its environment through learning process. 2.Inter-neuron connection strengths, known as synaptic weights, are used to store the acquired knowledge. • The procedure used to set the connection strengths is called learning

Basic Elements In Neural Network Structure • ANN performs fundamentally like a human brain. The cell body in the human neuron receives incoming impulses via dendrites. • Neurons of ANN consists of 3 main components; weights connecting the nodes, the summation function within the node, transfer function.

COMPONENTS OF NEURON

THE NEURON MODEL

• After the training process, ANN generalizes it. Generalization refers to the neural network producing reasonable outputs for inputs not encountered during training (learning). • These two information-processing capabilities make it possible for neural networks to solve complex problems.

Model of Artificial neuron

Properties of neural networks  Non-linearity  Input-Output mapping  Adaptivity

 Fault tolerance These are the properties that are most desirable for Solving the problems at hand.

Taxonomy

Neural networks

Feed-forward networks

Feed back networks

Feed-Forward Neural Network

Back Propagation Network • Back Propagation is a systematic method for training multi-layer artificial neural networks using back propagation of errors rule. • The aim of this network is to train the net to achieve a balance between the ability to respond correctly to the input patterns that are used for training and ability to provide good responses that are similar

Back Propagation neural network • The BP network consists of one input layer, one or more hidden layers, one output layer.

• The learning process includes two courses, one is the input information transmitting in the forward direction and another is the error transmitting in the backward direction.

Training Algorithm The training algorithm of back propagation involves 4 stages:  Initialization of weights  Feed-forward  Back propagation of errors  Updation of weights and biases

APPLICATION OF ANN’S • The application of ANN‟ s to short-term load forecasting has gained a lot of attention recently. • The availability of historical data is most important for ANN‟ s to apply to this field.

MATLAB An interactive system whose basic element is an array that does not require dimensioning It allows • Graphics • Computation • External interface It has in built tool boxes, which can also be extended by programming (SIMULINK)

NEURAL NETWORK TOOL BOX STEPS INVOLVED • Assemble the training data • Create the network object • Train the network • Simulate the network response to new inputs

Preprocessing and post processing • It’s useful to scale inputs & outputs such that they fall in specified range • So, the NN output needs de-scaling to generate forecasted loads

LOAD FORECASTING USING ANN • In this work NPDCL Warangal distribution system load data is considered for forecasting. • Temperature data was taken from the NITW weather station. • Feed Forward Back propagation 2-layered network structure with non-linear sigmoid function as transfer function is chosen.

Network Properties • The two layers include hidden layer and output layer. • The connection weights can be real numbers or integers. They are adjustable during the training, but some can be fixed deliberately. When training is completed, all of them should be fixed.

Load Forecasting with only loads as inputs • Input Variables • Different sets of lagged loads have been proposed as input features for the load prediction in the electricity market. Bearing in mind the daily and weekly periodicity and trend of the load signal, the set of • {L(h-1), L(h-2), L(h-3), L(h-4), L(h-5), L(h-6), L(h24), L(h-25), L(h-26), L(h-48), L(h-49), L(h-50), L(h-72), L(h-73), L(h-74), L(h-96), L(h-97), L(h98), L(h-120), L(h-121), L(h-122), L(h-144), L(h145), L(h-146), L(h-168), L(h-169), L(h-170), L(h192), L(h-193), L(h-194), } total of 30 inputs are used at input layer .

Topology Of ANN

(D-8)

(D-7)

L(h192) L(h193) L(h194)

L(h168) L(h169) L(h170)

…

(D-2)

(D-1)

(D)

L(h) … L(h-48) L(h-24) L(h-1) … L(h-49) L(h-25) L(h-2) Output

L(h-50) L(h-26) L(h-3) at L(h-4) Interva L(h-5) l L(h-6) „ h‟

Training: 1) The back propagation NN algorithm is used here for learning the neural network. 2) The implementation of Back Propagation involves a forward through the network to estimate the error, and then a backward modifying the synapses (weights) to decrease the error. Simulation: Using the trained neural network, the forecasting output is simulated using the test input patterns.

Simulation Results • • • • •

Number of input nodes =30; Number of hidden nodes=50; Number of output nodes=1; Number of training samples=10; Number of testing samples=5;

ACUTUAL LOAD

% ERROR

1256

FORECASTED LOAD 1417.7

1307

1390

6.3504

1153

1270.68

10.2064

992

910.73

8.1925

1028

920.87

10.42

12.8742

Load Forecasting By Considering Temperature Effect INPUT VARIABLES:

Hourly load data for the month January 2007 was collected from NPDCL (Northern Power Distribution Corporation Limited). Hourly temperature values were from the NITW weather station for the month January 2007. We used this data to train the network and test its performance.

Topology Of ANN

(D-3)

(D-2)

(D-1)

L(h-72) T(h-72) L(h-73) T(h-73) L(h-74)

L(h-48) T(h-48) L(h-49) T(h-49) L(h-50) T(h-50)

L(h-24) T(h-24) L(h-25) T(h-25) L(h-26)

T(h-74)

T(h-26)

(D)

Output

h, T(h) L(h) L(h-1),T(h-1) Load to be L(h-2), T(h-2) L(h-3), T(h-3) forecaste L(h-4), T(h-4) d at hour „h‟. L(h-5), T(h-5) L(h-6), T(h-6)

Simulation Results: • • • • •

Number of input nodes=32; Number of hidden nodes=50; Number of output nodes=1; Number of training samples=10; Number of testing samples=5;

ACUTUAL LOAD

FORECASTED LOAD

% ERROR

1028

1059.5

3.06

1200

1164.4

2.697

1185

1192.5

0.632

1159

1208

4.227

1174

1128.9

3.841

Adaptive neuro-fuzzy inference system • In ANFIS MF parameters are chosen so as tailor them to a set of i/p-o/p data. • First order sugeno fuzzy model with hybrid learning algorithm is used. • It constructs a set of fuzzy if-then rules with appropriate hip functions to generate the stipulated input-output pairs. • The parameters of MF’s and rules change through the learning process.

Fuzzy Inference System

1.Fuzzification interface: transforms input crisp values into fuzzy values

2.Knowledge base : A combination of rule base and data base. (i) Rule base containing a number of fuzzy ifthen rules (ii) Data base defines the hip functions of fuzzy sets used in the fuzzy rules. 3.Decision-making logic: performs inference for fuzzy control actions. 4.Defuzzification interface: transforms fuzzy value to a crisp value.

hip functions for seven linguistic variables

NB

Xmin

NM

NS

PS

PM

PB

Xmax

ANFIS Architecture • 1. If x is A1 and y is B1, then f1=p1x+q1y+r1 • 2. If x is A2 and y is B2, then f2=p2x+q2y+r2

Layer 1: Every node i in this layer is an adaptive node with a node function. O 1,i = µ A i (x) , for i=1,2 or O 1,i = µ B i-2 (y) , for i=3,4, Where x (or y) is the input to node i and Ai (or Bi-2) is a linguistic label (“small” or “large”) associated with the node . Here Gaussian hip function can be used.

Layer 2: Every node in this layer is a fixed node labeled Π, whose output is the product of all the incoming signals.

Layer 3: Here, the ith node calculates the ratio of the ith rule‟s firing strength to the sum of all rule‟s firing strength.

Layer 4: Every node i in this layer is an adaptive node with a node function.

Where wi is a normalized firing strength from layer 3 and {pi, qi, ri} is the parameter set of the node. These parameters are referred to as consequent parameters. Layer 5: The single node in this layer is a fixed node labeled Σ, which computes the overall output as the summation of all incoming signals:

Load Forecasting Using ANFIS: • INPUT VARIABLES: Hourly load data for the month January 2007 was collected from NPDCL (Northern Power Distribution Corporation Limited). Hourly temperature values were from the NITW weather station for the month January 2007. • We used this data to train the ANFIS and test its performance. Our focus is on a normal weekday.

Topology Of ANFIS Output L(h-2) T(h-2) Load and temperature at (h-2)

L(h-1) T(h-1) Load and temperature at (h-1)

„h‟, T(h), L(h) „h‟ is the hour Load to be of predicted forecasted at load hour „h‟

ANFIS editor: anfisedit

Simulation Results: • Number of input nodes=6; • Number of Memebership functions for each input=3; • Number of output nodes=1; • Number of hip function for output=1; • Number of training samples=38; • Number of testing samples=5;

Simulation Block Diagram

ACUTUAL LOAD

FORECASTED LOAD

% ERROR

1028

1035.5

0.727

1200

1192.4

0.633

1185

1179.5

0.464

1159

1167

0.69

1174

1169.9

0.349

Conclusions From the simulation results obtained we observed that the error in the load forecasting was decreased to a great extent when temperature effect was considered. The error was further decreased when simulated by ANFIS.

References • [1] G.Gross, F.D.Galiana, "Short-Term Load Forecasting," PrQceedings of IEEE, vo1.75, no.12, Dec. 1987, pp 1558-1 573. • [2] S.Rahman, R.Bhatnagar, "An Expert System Based Algorithm for Short Term Load Forecast," IEEE Trans. on Power Systems, vo1.3, no.2, May 1988, pp. 392-399 • [3] D.C.Park, M.A.El-Sharkawi, R.J.Mark 11, "Electric Load Forecasting Using An Artificial Neural Network," IEEE Trans. on Power Systems, vo1.6, no.2, May1991, pp.442- 449

[4] K.Y.Lee, Y.T.Cha, J.H.Park, "Short - Term Load Forecasting Using An Artificial Neural Network," IEEE Trans. on Power Systems, vo1.7, no. 1, Feb. 1992, pp. 124132 [5] S.T.Chen, D.C.Yu, A.R.Moghaddamjo, "Weather Sensitive Short-Term Load Forecasting Using Nonfully Connected Artificial Neural Network," IEEE Trans. on Power Systems, vo1.7, no.3, Aug. 1992, pp.1098-1105 [6] Y.T.Park, J.K.Park, "An Expert System for Short Term Load Forecasting by Fuzzy Decision," Proc. of 2nd Symp. on Expert System Application to Power Systems, July 1989, Washington, USA, pp.244-250

THANK YOU