This essay was made by and copyrighted to Mr. Radhakrishnan Poomari.

ARTIFICIAL NEURAL NETWORKS FOR INTELLIGENT
REAL-TIME POWER QUALITY MONITORING SYSTEM.

ABSTRACT:

Most of the modern industrial power quality monitoring systems are used for pre-fault alarming and load flow analysis. In this paper, an Artificial Neural network (ANN) model for intelligent utilization of power for monitoring the power quality is presented. The online monitoring, voltage and current are fed into the network after preprocessing of Harmonics and waveform abnormalities. The performance of the proposed method is evaluated by comparing the test results with the actual expected values.

KEYWORDS:

Active power, reactive power, apparent power, power quality, power factor prediction, Harmonics classification, neural networks.

INTRODUCTION:

A wide variety of real time power quality monitoring systems are serving the power industry. A quick review will show that most of the monitoring systems are used just to track the quality of power supply and for load flow analysis. For the monitoring systems to be more intelligent, the use of feed forward Artificial Neural Networks (ANN) for predicting the trend of power factor, reactive power and active power is proposed. By predicting the power factor and active power demand it is possible to automate the control of reactive power load and to better utilize the volt-amperes (VA) inflow. Efficient usage of the VA loading will not only improve the overall grid condition but also reduce the consumer’s industrial tariffs. Depending upon the predicted power factor, power factor corrective measures could be turned on or off to control the VA inflow into the plant. This prediction system will be extremely useful for automated control of power inflow, especially in the countries where there are limitations on the usage of consumers’ peak VA maximum demand.

Modern complex manufacturing systems rely heavily on Computer Numerical Controlled (CNC) machines, variable speed drives and robotic devices which often require a high reliability from the incoming electricity supply. Due to the widespread usage of non-linear loads there has been a significant increase in the harmonic content of the 3-phase supply, raising serious power quality issues. An attempt is made for classification of harmonics and abnormal waveforms using Artificial Neural Networks. Among the commonly used neural network models, Self-Organizing Maps (SOM) are reputed for the pattern classification. But the feed forward neural networks are more efficient and promising than the SOM.

PRACTICAL IMPORTANCE OF REACTIVE POWER CONTROL:

The ratio of active power (P) measured in watts to the apparent power (S) in volt-amperes is termed the power factor:

Power factor = cos(f) = P/ S = resistance (R) / impedance ( Z)

It has become a normal practice to say that power factor is lagging when the current lags the supply voltage and leading when the current leads the supply voltage. This means that the supply voltage is regarded as the reference quantity. A majority of the loads served by a power utility draw current at a lagging power factor. When the power factor of the load is unity, active power equals apparent power (P=S).But, when the power factor of the load is less than unity, say 0.6, the power utilized is only 60%.This means that 40% of the apparent power is being utilized to supply the reactive power, VAR, demand of the system. It is therefore clear that the higher the power factor of the load, the greater the utilization of the apparent power. For the generating and transmission stations, lower the power factor the larger must be the size of the source to generate that power, and greater must be the cross-sectional area of the conductor to transmit it. In other words, the greater is the cost of generation and transmission of the power. Moreover, lower power factor will also increase the I2R losses in lines/equipments as well as result in poor voltage regulation.

POWER QUALITY ISSUES:

The interest in power quality has increased during the latest years. A power quality problem can be defined as “a problem due to frequency, voltage regulation, voltage dips, flicker, transients, harmonics, and power factor and 3-phase imbalance”. All machines affect the grid by the production of harmonics, voltage variations or by their power factors. At the same time the machines is increasing rapidly and thereby the power quality is being further affected. Machine drives can be disturbed by transients or other irregularities in the feeding voltage. The drives may as well disturb the network voltage by the production of harmonics, load changes and varying power factor. The harmonic content and magnitude existing in any power system is largely unpredictable, and their effects will vary widely in different parts of the same system due to varying effects of different frequencies. Since the distorted wave is in the supply system, harmonic effects may occur at any point on the system where the distorted waveform exists. This occurrence is not limited to the immediate vicinity of the harmonic-producing device. When power is converted to direct current or some other frequency, harmonics will exist in any distorted alternating component of the converted power. Harmonics may be transferred from one circuit or system to other by direct connection or by inductive or capacitive coupling. Harmonics of 50 Hz are in the low frequency audio range, the transfer of these frequencies into communication, signaling, and control circuits employing frequencies in the same range may cause unacceptable interference. In addition, harmonic currents circulating within a power circuit reduce the capacity o the current carrying equipment and increase losses without providing any useful work.

Conventional power monitoring systems are capable of identifying most of the power quality issues as well as classification of harmonics and abnormal waveforms. To further argument robustness in monitoring and to improve performance during worst conditions, the use of Neural networks as an alternative method for classification of the various types of harmonics and abnormal waveforms if proposed.

ARTIFICIAL NEURAL NETWORKS AND TRAINING GUIDELINES:

A neural network is characterized by the architecture, the connection strength between pairs of neurons (weights), node properties, and updating rules. An important feature of the artificial neural network (ANN) is its capability to learn and generalize from a set of training data. ANN can learn by adapting its weights to changes in the surrounding environment, can handle imprecise information, and are able to generalize from known tasks to unknown ones. The success of the ANN performance depends upon how accurate and generalisable the learning has been. There are three broad paradigms of learning: supervised, unsupervised (or self-organized) and reinforcement learning (a special case of supervised learning). The core difference between supervised and unsupervised learning is that in supervised learning the system directly compares the network output with a known correct or desired answer, whereas in unsupervised learning the output is not known. Unsupervised training allows the neurons to compete with each other until winners emerge. The resulting values of the winner neurons determine the class to which a particular data set belongs. Reinforcement learning is a form of supervised learning where the adaptive neuron receives feedback from the environment that directly influences learning.

In supervised learning, the training patterns can be thought of as a set of ordered pairs {(x1, y1). (x2, y2),…, (xp, yp)} where xi represents an input pattern and yi represents the output pattern vector associated with the input vector xi. The process of training the network is of finding the gradient of the error surface (in weight space) of the actual output produced by the network with respect to the desired result.

The following guideline will be of help as a step by step methodology for training a network.

• Choosing the number of neurons :
  The number of hidden neurons affect how well the network is able to separate the data. A large number of hidden neurons will ensure correct learning and the network is able to correctly predict the data it has been trained on, but its performance on new data, its ability to generalize, is compromised. With too few hidden neurons, the network may be unable to learn the relationships amongst the data and the error will fail to fall below an acceptable level. Thus, selection of the number of hidden neurons is a crucial decision. Often a trial and error approach is taken starting with a modest number of hidden neurons and gradually increasing the number if the network fails to reduce its error. A much used approximation for the number of hidden neurons for a three layered network is N=1/2 (J+K) +vP, where J and K are the number of input neurons and P is the number of patterns in the training set.
• Choosing initial weights:
  The learning algorithm uses steepest descent technique, which rolls straight downhill in weight space until the first valley is reached. This valley may not correspond to a zero error for the resulting network. This makes the choice of initial starting point in the multidimensional weight space critical. However, there are no recommended rules for this selection except trying several different weight values to see if the network results are improved.
• Choosing the learning rate:
  Learning rate effectively controls the size of the step that is taken in multidimensional weight space when each weight is modified. If the selected learning rate is too large then the local minimum may be over stopped constantly, resulting in oscillations and slow convergence to lower error state. If the learning rate is too low, the number of iterations required may be too large, resulting in slow performance. Usually the default values of most commercial neural network packages are in the range 0.1-0.3 providing a satisfactory balance between the two consequences. If the network fails to reduce its error, then reducing the learning rate may help improve convergence to a local minimum of the error surface.
• Choosing the activation function:
  The learning signal is a function of the error multiplied by the gradient of the activation function df/d(net). The larger the value of the gradient, the more weight the learning will receive. For training, the activation function must be monotonically increasing from left to right, differentiable and smooth.

PARAMETERS TO BE PREDICTED:

The experimental system consists of three stages: Problem modeling and data simulation, network training and performance evaluation.

A heavy engineering plant should be considered for the prediction of power factor, reactive power and active power. For a typical 24-hour load demand pattern of the plant 1440 data sets were generated. The input parameters to be considered are voltage and current. The voltage (V) should be taken as a random value (i.e. +/- 2.5% of the normal value) to cater for the worst conditions in the grid voltage regardless of the plant load. Using the known values of current(I), power factor (cosf) and random value of voltage, active power and reactive power values should be calculated.