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

This paper introduces a probabilistic method for the ranking of influential uncertain parameters for the accurate assessment of power system voltage stability. Future power systems will be highly interconnected and complex with a variety of uncertain parameters such as the injection of intermittent renewable energy resources, the adoption of flexible hierarchical control structures and the appearance of new types of loads. Identifying and ranking the uncertain parameters are important in future power system operations since they can provide referable indexes for system operators to achieve better system management with less monitoring. This paper presents the probabilistic method for the identification and ranking of critical uncertain parameters. A modified version of the 68 bus NETS-NYPS test system is used in this study for simulation studies. The effects of uncertain parameters are modelled with Monte-Carlo method in the environments of MATLAB and DIgSILENT PowerFactory. The performances of the ‘nose-point area’ of P-V Curves for system load buses are used as indexes when evaluating their sensibility for specific uncertainties.

/pdf/probabilistic-ranking-of-critical-parameters-affecting-1669x3ogto.pdf

Probabilistic ranking of critical parameters affecting voltage stability in network with renewable generation

Modern Power Systems are equipped with new technologies like renewable energy sources (RES) and flexible power-consuming devices. These new technologies introduce uncertainties in system generating and loading profiles which in turn affect the dynamic characteristics, and the stable operation of the system might be at risk. This paper employs sensitivity analysis method for the identification and ranking of critical uncertain parameters affecting transient stability in a large meshed network with renewable generation. Copula method is used in this paper in order to model the correlations between uncertain parameters based on real system data. The paper develops methodology for identifying influential parameters which have the dominant effect on network transient stability behaviour. “Heat Map” is used as graphical representation of the results on which the influence of system uncertainties is clearly demonstrated. Economic and optimal operation of the power system in terms of stability can be achieved through concentrating resources in the monitoring and fine-tuning of the identified critical parameters. Keywords-Copula method, renewable generation, sensitivity analysis, transient stability

/pdf/power-system-transient-stability-analysis-in-networks-with-2pazjbxmnb.pdf

Power system transient stability analysis in networks with renewable generation considering variable correlations

The paper proposes a method to derive an equivalent age from asset condition scores in order to incorporate asset condition into existing reliability assessment techniques. The method is related to end-of-life failure to inform replacement decision-making process. The paper projects the age cumulative distribution function (CDF) of a fleet of power transformers into the cumulative distribution function (CDF) of their condition scores. A relationship between condition score and age was formulated by using curve fitting techniques. Case studies were performed on a generic test system to compare system and load point reliability indices using the chronological age and the derived equivalent age. The results showed that using equivalent age resulted in different critical load points than the ones identified when using chronological age.

Deriving Transformer Equivalent Age for Power System Reliability Assessment from Asset Condition Score

This paper presents commissioning details of a coordinated reactive power-voltage controller (CQVC) installed in a multi-machine steam power plant (SPP). The CQVC regulates reactive power and voltage of a 1992MVA multi-machine SPP. After briefly introducing basic control principles and relevant details about the CQVC's implementation, CQVC parameterization and tuning are thoroughly discussed. Once commissioned the CQVC performance under various operating conditions is assessed. It is shown that the CQVC successfully maintains a HV busbar voltage and allocates reactive power to participating generators in accordance to their capability. Numerous CQVC responses recorded at the site are presented to demonstrate controller's performance under normal and extreme plant and network operating conditions.

http://ieeexplore.ieee.org/iel7/6916492/6938773/06939196.pdf

Jovica V. Milanovic

Papers

Probabilistic ranking of critical parameters affecting voltage stability in network with renewable generation

Power system transient stability analysis in networks with renewable generation considering variable correlations

Deriving Transformer Equivalent Age for Power System Reliability Assessment from Asset Condition Score

Robustness of commissioned coordinated Q-V controller for multi-machine power plant

Modelling and Aggregation of Loads in Flexible Power Networks