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

The Compact Muon Solenoid (CMS) detector is described. The detector operates at the Large Hadron Collider (LHC) at CERN. It was conceived to study proton-proton (and lead-lead) collisions at a centre-of-mass energy of 14 TeV (5.5 TeV nucleon-nucleon) and at luminosities up to 10(34)cm(-2)s(-1) (10(27)cm(-2)s(-1)). At the core of the CMS detector sits a high-magnetic-field and large-bore superconducting solenoid surrounding an all-silicon pixel and strip tracker, a lead-tungstate scintillating-crystals electromagnetic calorimeter, and a brass-scintillator sampling hadron calorimeter. The iron yoke of the flux-return is instrumented with four stations of muon detectors covering most of the 4 pi solid angle. Forward sampling calorimeters extend the pseudo-rapidity coverage to high values (vertical bar eta vertical bar <= 5) assuring very good hermeticity. The overall dimensions of the CMS detector are a length of 21.6 m, a diameter of 14.6 m and a total weight of 12500 t.

/pdf/the-cms-experiment-at-the-cern-lhc-4d2umuzboo.pdf

The CMS experiment at the CERN LHC

An Introduction to MultiAgent Systems.

The Smart Grid, regarded as the next generation power grid, uses two-way flows of electricity and information to create a widely distributed automated energy delivery network. In this article, we survey the literature till 2011 on the enabling technologies for the Smart Grid. We explore three major systems, namely the smart infrastructure system, the smart management system, and the smart protection system. We also propose possible future directions in each system. colorred{Specifically, for the smart infrastructure system, we explore the smart energy subsystem, the smart information subsystem, and the smart communication subsystem.} For the smart management system, we explore various management objectives, such as improving energy efficiency, profiling demand, maximizing utility, reducing cost, and controlling emission. We also explore various management methods to achieve these objectives. For the smart protection system, we explore various failure protection mechanisms which improve the reliability of the Smart Grid, and explore the security and privacy issues in the Smart Grid.

/pdf/smart-grid-the-new-and-improved-power-grid-a-survey-4jypbbgv3j.pdf

Smart Grid — The New and Improved Power Grid: A Survey

Smart Grid - The New and Improved Power Grid:

In a power system with significant wind power penetration, the tripping of wind turbines for a system fault condition can be a major concern to the system operator. With wind turbines employing different under-voltage protection settings available in the system, a fault on a transmission line can lead to tripping of a large number of wind farms depending on the voltages at the wind farm buses during the fault and the protection settings of the wind farms. As a result, an N-l contingency may evolve into an N-(K+1) contingency, where K is the number of wind farms tripped due to low voltage conditions during a fault. The severity of such a condition depends on the output of the wind farms during a fault, and if it coincides with the high wind and off peak loading condition, it might lead to system instabilities. Therefore, it is important for the system operator to be aware of such limiting events during system operation and be prepared to take proper control actions. This can be achieved by incorporating the wind farm tripping status during N-1 static security assessment procedure. In this paper a methodology based on Z-bus algorithm is proposed to determine the tripping status of wind farms for a worst case fault, so that it can be used in contingency evaluation procedure. The proposed algorithm is implemented in MATLAB and tested with a 23 bus test system.

Tripping of wind turbines during a system fault

Relays can degrade power system performance if they fail or are set incorrectly. Reports have shown that this degradation can lead to cascading outages. This paper will show how real-time communication with relays can help prevent these consequences. Through laboratory simulations, it is shown that real-time communication to protective relays can be achieved. This paper reports a new system that adapts automatic relay responses to make the power system more secure. The method of operation is explained.

Adaptation of relay operations in real-time

Proper coordination of the protective relays is one of the important conditions for power system security Settings of distance relays usually determined by heuristic rules may not satisfy the coordination requirements In this paper, the coordination behaviour of the setting rules of the distance relays is investigated Coordination conditions and properties are derived and the coordination region is introduced Efficient algorithms to identify the coordination status are presented together with its test results

Intelligent approach to coordination identification in distance relaying

In current restructured wholesale power markets, the short length of time series for prices makes it difficult to use empirical price data to test existing price forecasting tools and to develop new price forecasting tools. This study therefore proposes a two-stage approach for generating simulated price scenarios based on the available price data. The first stage consists of an Autoregressive Moving Average (ARMA) model for determining scenarios of cleared demands and scheduled generator outages (D&O), and a moment-matching method for reducing the number of D&O scenarios to a practical scale. In the second stage, polynomials are fitted between D&O and wholesale power prices in order to obtain price scenarios for a specified time frame. Time series data from the Midwest ISO (MISO) are used as a test system to validate the proposed approach. The simulation results indicate that the proposed approach is able to generate price scenarios for distinct seasons with empirically realistic characteristics.

/pdf/scenario-generation-for-price-forecasting-in-restructured-4jjfj82jmq.pdf

Scenario generation for price forecasting in restructured wholesale power markets

The growing number of consumer-grade network-enabled Distributed Energy Resources (DER) installations introduces new attack vectors that could impact grid operations through coordinated attacks. This work presents a cyber-physical model and risk assessment methodology for analyzing the emerging nexus between Internet of Things-based energy devices and the bulk transmission grid. The cyber model replicates the device-level interconnectivity and software components interaction found within these architectures to understand the feasibly of coordinated attacks, while the physical model is used to assess the attack's impacts on the grid. The manuscript questions the validity of previous papers' claims regarding IoT-based grid attacks by addressing key limitations in both the power grid and cyber infrastructure models of those works. The resulting methodology is then evaluated using the Western Electricity Coordinating Council (WECC) electrical model coupled with DER's operational statistics from California. The results suggest that current DER penetration rates are not yet significant enough to present serious risk, but continued DER growth may be problematic. Furthermore, the work identifies policies that mitigate these risks through increased device diversity and cybersecurity requirements.

/pdf/assessing-cyber-physical-risks-of-iot-based-energy-devices-2ncpvtpko9.pdf

Chen-Ching Liu

Papers

Tripping of wind turbines during a system fault

Adaptation of relay operations in real-time

Intelligent approach to coordination identification in distance relaying

Scenario generation for price forecasting in restructured wholesale power markets

Assessing Cyber-Physical Risks of IoT-Based Energy Devices in Grid Operations