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.

Differential evolution (DE) is arguably one of the most powerful stochastic real-parameter optimization algorithms in current use. DE operates through similar computational steps as employed by a standard evolutionary algorithm (EA). However, unlike traditional EAs, the DE-variants perturb the current-generation population members with the scaled differences of randomly selected and distinct population members. Therefore, no separate probability distribution has to be used for generating the offspring. Since its inception in 1995, DE has drawn the attention of many researchers all over the world resulting in a lot of variants of the basic algorithm with improved performance. This paper presents a detailed review of the basic concepts of DE and a survey of its major variants, its application to multiobjective, constrained, large scale, and uncertain optimization problems, and the theoretical studies conducted on DE so far. Also, it provides an overview of the significant engineering applications that have benefited from the powerful nature of DE.

/pdf/differential-evolution-a-survey-of-the-state-of-the-art-3lz840pz2t.pdf

Differential Evolution: A Survey of the State-of-the-Art

Impatti, adattamento e vulnerabilita Le cause e le responsabilita dei cambiamenti climatici sono state trattate sul numero di ottobre della rivista Cda. Approfondiamo l’argomento presentando il documento: “Cambiamenti climatici 2007: impatti, adattamento e vulnerabilita” votato ad aprile 2007 dal secondo gruppo di lavoro del Comitato Intergovernativo sui Cambiamenti Climatici (Intergovernmental Panel on Climate Change). Si tratta del secondo di tre documenti che compongono il quarto rapporto sui cambiamenti climatici.

/pdf/climate-change-2007-impacts-adaptation-and-vulnerability-31xc1cf4d3.pdf

Climate Change 2007: Impacts, Adaptation and Vulnerability.

The on-going restructuring of electric power utilities poses great challenges for power system engineers to plan and operate power systems as economical and reliable as possible. This paper discusses an important issue, which has been usually neglected, when quantifying active power transfer levels in the present economic-driven electricity markets. A mathematical model of a multi-objective optimisation (MOOP) technique has been adopted and presented here for transfer capability studies; which can be helpful for power system planning and operation procedures. The newly-developed algorithm is being tested on several case studies with relevant results to aid discussions.

/pdf/evaluating-transfer-capability-of-economic-driven-power-4rgb7g20q9.pdf

Evaluating Transfer Capability of Economic-driven Power Markets

The reconstruction and deregulation have brought fundamental changes to many aspects of power system operation and management. As a result, the planning activity is no longer dominated by the system operator. The deregulation has also brought many uncertainties and constraints to the system planning area. Therefore, the traditional centralized expansion planning approach will face difficulties in a market environment and new planning approaches are needed. In this paper, a market-oriented planning objective for transmission network expansion has been developed, which aims at maximizing the overall benefit from network expansion while considering critical constraints, such as power flow balance and transmission capacities. The planning objective has been solved by a genetic algorithm (GA) to achieve the best available expansion plan. The IEEE 14-bus system is used to test the developed method.

Market-based planning of transmission network using genetic algorithm

/pdf/editorial-machine-learning-to-support-low-carbon-energy-1wqmw4jq.pdf

Editorial: Machine learning to support low carbon energy transition

To ensure a successful bid while maximizing of profits, generation companies (GENCOs) need a self-scheduling strategy that can cope with a variety of scenarios. So distributionally robust opti-mization (DRO) is a good choice because that it can provide an adjustable self-scheduling strategy for GENCOs in the uncertain environment, which can well balance robustness and economics compared to strategies derived from robust optimization (RO) and stochastic programming (SO). In this paper, a novel mo-ment-based DRO model with conditional value-at-risk (CVaR) is proposed to solve the self-scheduling problem under electricity price uncertainty. Such DRO models are usually translated into semi-definite programming (SDP) for solution, however, solving large-scale SDP needs a lot of computational time and resources. For this shortcoming, two effective approximate models are pro-posed: one approximate model based on vector splitting and an-other based on alternate direction multiplier method (ADMM), both can greatly reduce the calculation time and resources, and the second approximate model only needs the information of the current area in each step of the solution and thus information private is guaranteed. Simulations of three IEEE test systems are conducted to demonstrate the correctness and effectiveness of the proposed DRO model and two approximate models.

A Distributionally Robust Self-Scheduling Under Price Uncertainty Based on CVaR.

In order to avoid the shortcoming of faceted classification scheme for being not flexible enough, in this paper, an integrated method which combining the advantages of faceted classification scheme and key value pair method is proposed to represent the logical model of software component. The faceted classification scheme provides a set of summarized optional information for software component to choose. And the key value pair method uses key and value to express the information contained in software component. The information contained in a software component can be divided into four basic facets, namely, the application field, expression method, using environment, development process. And they describe the basic information, using information, and storage information of a software component. The component management protocol based on URL is defined to represent software component, which can be used for storing, transmitting, and analyzing of software component inside of system.

Zhao Yang Dong

Papers

Evaluating Transfer Capability of Economic-driven Power Markets

Market-based planning of transmission network using genetic algorithm

Editorial: Machine learning to support low carbon energy transition

A Distributionally Robust Self-Scheduling Under Price Uncertainty Based on CVaR.

A Software Component Library Implemented by Using Faceted Classification Scheme and Component Management Protocol