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

Contribution to Bulk System Control and Stability by Distributed Energy Resources connected at Distribution Network

Dynamic load modelling based on measurements in medium voltage distribution network

This paper critically evaluates a number of sensitivity analysis (SA) techniques to identify the most influential parameters affecting power system small-disturbance stability. SA of uncertain parameters has attracted increased attention with the adoption of deregulated market structure, intermittent energy resources, and new types of loads. Identification of the most influential parameters affecting system stability using SA techniques will facilitate better operation and control with reduced monitoring (only of the parameters of interest) by system operators and stakeholders. In total, nine SA techniques have been described, implemented, and compared in this paper. These can be categorized into three different types: local, screening, and global SA. This comparative analysis highlights their computational complexity and simulation time. The methods have been illustrated using a two-area power system and 68 bus NETS-NYPS test system. The priority ranking of all uncertain parameters has been evaluated, identifying the most critical parameters with respect to the small-signal stability of the test systems. It is shown that for many applications, the Morris screening approach is most suitable, providing a good balance between accuracy and efficiency.

/pdf/priority-ranking-of-critical-uncertainties-affecting-small-4tmy0gwoit.pdf

Priority Ranking of Critical Uncertainties Affecting Small-Disturbance Stability Using Sensitivity Analysis Techniques

This paper presents an approach to optimally select and allocate flexible ac transmission (FACTS) devices in a distribution network in order to minimize the number of voltage sags at network buses. The method proposed is based on the optimization of a preselected objective function using simple and niching genetic algorithms (GA). The objective of the optimization is to achieve the improvement in overall system sag performance of the network. Using proposed GA-based optimization, the location, the type and the rating of six (in total) FACTS devices are optimized simultaneously. Three types of FACTS devices are implemented in this study, namely, static var compensator, static compensator, and dynamic voltage restorer. The performance of the proposed algorithm is tested and illustrated on 295-bus generic distribution system.

Global Voltage Sag Mitigation With FACTS-Based Devices

The paper describes genetic-algorithm (GA)-based optimization software for reconfiguration of a distribution network in order to minimize financial losses due to voltage sags. The developed methodology starts with a selected number of switches which generate various topologies. Load flows are then performed to evaluate the feasibility of topologies. For each feasible topology, fault analysis is performed to first calculate voltage sags at different buses in the network and then to calculate financial losses incurred by voltage sags at buses with sensitive industrial processes. The result of the optimization is the topology which yields the lowest voltage sag cost to customers. The main features of the GA include double-point crossover and adaptive mutation. The developed software tool is applied to the 295-bus generic distribution system.

Jovica V. Milanovic

Papers

Contribution to Bulk System Control and Stability by Distributed Energy Resources connected at Distribution Network

Dynamic load modelling based on measurements in medium voltage distribution network

Priority Ranking of Critical Uncertainties Affecting Small-Disturbance Stability Using Sensitivity Analysis Techniques

Global Voltage Sag Mitigation With FACTS-Based Devices

Minimization of Voltage Sag Costs by Optimal Reconfiguration of Distribution Network Using Genetic Algorithms