There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Data Mining - Concepts and Techniques.

Data Mining Practical Machine Learning Tools and Techniques

The paper examines parallel operation of two adjacent steam power plants (SPP) under coordinated reactive power (Q) - voltage control. A coordinated reactive power-voltage controller (CQVC) performs optimal coordination of the synchronous generators' Q outputs in order to maintain the voltage at a SPP HV busbars. When the plants are equipped with CQVC, they are both trying to control the same voltage, so the Q oscillations may occur due to high level of coupling. Before the commissioning of the second CQVC detailed laboratory testing was performed to determine under which conditions the oscillations may occur. The impact of all generators on HV busbars voltage is determined first. Then the worst case scenario is chosen for the most influential generators, i.e., when both CQVCs act simultaneously and independently. The laboratory test rig is developed for CQVC testing. The results showed that coordinated control of influential generators results in stable operation and ensures uniform Q share among involved generators which leads to better power system voltage support.

Parallel operation of two adjacent steam power plants under coordinated Q-V control

The paper presents analysis of the torsional torques of a turbine generator rotor system in a meshed AC network with monopolar HVDC link following symmetrical and asymmetrical faults. The emphasis of the work is on establishing the influence of uncertainties in the mechanical parameters of turbine-generator shaft system on maximum torsional torques. Three loading conditions of turbine generator are considered and different types of faults are simulated for each loading condition. A full multi stage turbine model, a four machine meshed AC network and a classical, Line Current Commutated, HVDC system model are developed in DIgSILENT Power Factory environment. Uncertainties in mechanical parameters of turbine-generator shafts are modeled using probability density functions to assess more realistically their effects on maximum torsional torques.

Effects of uncertainties in shaft mechanical parameters on maximum torsional torques in meshed networks with HVDC lines

This paper presents the methodology developed to derive the linear and nonlinear load composition of an aggregate harmonic load model based on harmonic measurements taken at the service entrance feeder. Based on harmonic current spectra of typical nonlinear loads and aggregate harmonic loads obtained through measurement at service entrance, a weighted coefficient representative of the percentage combination of each type of nonlinear load is determined by solving a set of simultaneous equations with complex variables. Subsequently, linear load fraction is determined through SUPERHARM simulation of the modeled aggregate load.

/pdf/establishment-of-load-composition-in-aggregate-harmonic-load-1is5wcw8dv.pdf

Establishment of load composition in aggregate harmonic load model at LV buses based on field measurements

A generic method is proposed in this paper to integrate VSC terminals into AC systems taking into account the cascaded VSC control structure. The method allows the VSC models to be developed separately by considering them as current injections into the connected AC system, and therefore provides an alternative for quickly integrating new VSC models into conventional power system models. The method can also be applied to Multi-Terminal DC (MTDC) grid integration provided with an available AC/DC load flow. The integrated system model developed based on this method is suitable for small signal analysis and controller designs. Modal analysis techniques can be readily applied to the whole integrated AC/DC model and the effects of VSC controls on the AC system power oscillations can be analysed mathematically.

Jovica V. Milanovic

Papers

Parallel operation of two adjacent steam power plants under coordinated Q-V control

Effects of uncertainties in shaft mechanical parameters on maximum torsional torques in meshed networks with HVDC lines

Establishment of load composition in aggregate harmonic load model at LV buses based on field measurements

Integrated AC/DC model for power system stability studies

Self-disconnection and Self-recovery of Loads Due to Voltage Sags and Short Interruptions