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 placement of FACTS devices in a power network is of great importance to ensure the utilization of the full potential of the transmission network. In this study firstly, a static VAr compensators (SVCs) are placed optimally in a power network by taking into consideration the generation costs of both active and reactive power and the cost of the SVCs. The optimal power flow (OPF) and the low discrepancy sequences (LDS) based optimization procedure are employed to solve the problem of optimal allocation of SVCs. Secondly, a small disturbance stability study is performed in order to investigate how installing the SVCs with additional control loops at such locations could contribute to system small disturbance stability. The study demonstrated that the optimal allocation of SVCs is a cost effective measure since the installed SVCs reduce overall generation costs and additionally contribute to the enhancement of the security of the transmission network by improving the damping of electromechanical oscillations

Placement and Tuning of SVCs for the Improvement of Techno-economic Performance of the Network Based on Sequential Number Theoretic Optimization Algorithm

This paper investigates the influence of load modeling on voltage sag characteristics and compares the results of voltage sag calculation with different load models. It is shown that some voltage sag characteristics are strongly influenced by the models chosen for representing power system loads. Therefore, depending on the aims of the voltage sag study, load models need to be carefully chosen.

Load modeling for voltage sag studies

https://www.research.manchester.ac.uk/portal/files/86497860/Techno_economic_analysis_of_global_power_quality_mitigation_strategy_for_provision_of_differentiated_quality_of_supply.pdf

Techno-economic analysis of global power quality mitigation strategy for provision of differentiated quality of supply

Load modelling attracts renewed interests these days in maintaining peak load conditions, supplying new types of loads and accommodating more renewable generation into electricity networks. This work describes real measurement data acquisition and step-by-step signal processing for developing aggregate load models at 11kV and 6.6kV level. Challenges in analyzing real measurement data are highlighted and issues to improve measurement-based load modelling are discussed. Load models at 15 substations from a UK distribution network are presented with subsequent model parameters. These load models will provide an insight to the operational flexibility, network resilience and management requirements of the measurement sites and related up-and-downstream substations.

/pdf/a-step-by-step-data-processing-guideline-for-load-model-4hi4zgn3nw.pdf

A step-by-step data processing guideline for load model development based on field measurements

Power system loads have been proven to have a significant influence on power system stability, and their accurate modelling is essential for reliable assessment of dynamic system behaviour. This study first applies an efficient sensitivity analysis method, to rank power system load model parameters based on their influence on system voltage, frequency, and angular stability considering a range of load models, operating conditions, and parameter correlations. Following this, the required accuracy levels of identified critical parameters for different types of stability studies are determined. Finally, this study demonstrates the importance of modelling correlation between load model parameters on establishing the parameter accuracy requirements for different types of stability studies. The practical significance of the approach is in enabling power system operators to identify and focus on accurate (with specified accuracy) modelling of only a subset of loads while being confident that the accuracy of system stability studies will not be compromised.

https://ietresearch.onlinelibrary.wiley.com/doi/pdf/10.1049/iet-gtd.2019.0489

Jovica V. Milanovic

Papers

Placement and Tuning of SVCs for the Improvement of Techno-economic Performance of the Network Based on Sequential Number Theoretic Optimization Algorithm

Load modeling for voltage sag studies

Techno-economic analysis of global power quality mitigation strategy for provision of differentiated quality of supply

A step-by-step data processing guideline for load model development based on field measurements

Ranking and quantifying the effects of load model parameters on power system stability