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:

Consensus weighting of a multi-agent system for load shedding

In areas with high wind power penetration, the protection of transmission lines from overload during critical contingencies is an important issue. The objective of this research is to formulate the technical problem and develop a methodology to solve the problem associated with overloading of transmission facilities in high wind generation areas. The proposed method is to curtail the wind turbine outputs through the Energy Management System facilities in the on-line operational environment. The proposed method, which is based on linear optimization, sends the calculated control signals via the Supervisory Control and Data Acquisition (SCADA) system to wind farm controllers. The necessary ramping of the wind farm outputs is implemented by the appropriate blade pitch angle control at the turbine level. The curtailment strategy is tested with an equivalent system model of MidAmerican Energy Company (MEC). The results show that the line overload in high wind generation areas can be alleviated by controlling the outputs of the wind farms step-by-step over an allowable period of time. Copyright © 2008 John Wiley & Sons, Ltd.

Wind generation curtailment to relieve line overload in an on-line environment

The electric distribution system is becoming more complex with increasing visibility, and a variety of control devices for voltage and power factor control. These advancements provide improved observability of system status and let the operator control the system in more efficient ways. Smart meters are measurement devices that allow the operator to acquire accurate information about the end consumers, and state of the system. Smart meters provide the opportunity to revisit traditional distribution system models in an effort to improve them with more accurate information. Smart meter data enables the creation of time-varying load based distribution system models, enabling testing of various control algorithms. This paper purposes a method for developing a time-series distribution power-flow model using text-based AMI load data which may contain calculation failures. As a test case, a real distribution feeder is modeled in the open source distribution software GridLAB-D, with seasonal loading scenarios. The results are verified by DMS data obtained from the utility. The proposed method does not require GIS data for creating distribution system model. and also provides ways to deal with had data.

Modeling of Electric Distribution Feeder Using Smart Meter Data

Based on data available from phase measurement units (PMUs), this paper proposes an energy margin constrained online coordinated voltage control (CVC) algorithm. First, the energy function model is established, which is based on detailed device models that include the effects of shunt capacitor banks, reactive power output of generators and under-load-tap-changers (ULTCs). In order to improve the computational efficiency, a Lie derivative-based method is used to map the energy change into the system trajectory along the energy manifold. Then, the change of energy margin based on the Lie derivative is used as the objective function and the reactive power margin is used as a constraint to formulate a linear programming problem. A coordinated strategy is proposed to help achieve the optimal solution when the linear programming problem is solved. In comparison with the other control modes, the proposed method improves the stability margin and the control effectiveness of voltage profile. Numerical results are provided for a three-machine system, the IEEE-30 bus system and the New England-39 bus benchmark system.

Coordinated Voltage Control With Online Energy Margin Constraints

Resilient and reliable operation of cyber physical systems of societal importance such as Smart Electric Grids is one of the top national priorities. Due to their critical nature, these systems are equipped with fast-acting, local protection mechanisms. However, commonly misguided protection actions together with system dynamics can lead to un-intentional cascading effects. This paper describes the ongoing work using Temporal Causal Diagrams (TCD), a refinement of the Timed Failure Propagation Graphs (TFPG), to diagnose problems associated with the power transmission lines protected by a combination of relays and breakers.
The TCD models represent the faults and their propagation as TFPG, the nominal and faulty behavior of components (including local, discrete controllers and protection devices) as Timed Discrete Event Systems (TDES), and capture the cumulative and cascading effects of these interactions. The TCD diagnosis engine includes an extended TFPG-like reasoner which in addition to observing the alarms and mode changes (as the TFPG), monitors the event traces (that correspond to the behavioral aspects of the model) to generate hypotheses that consistently explain all the observations. In this paper, we show the results of applying the TCD to a segment of a power transmission system that is protected by distance relays and breakers.

/pdf/temporal-causal-diagrams-for-diagnosing-failures-in-cyber-2jws6a7rep.pdf

Chen-Ching Liu

Papers

Consensus weighting of a multi-agent system for load shedding

Wind generation curtailment to relieve line overload in an on-line environment

Modeling of Electric Distribution Feeder Using Smart Meter Data

Coordinated Voltage Control With Online Energy Margin Constraints

Temporal Causal Diagrams for Diagnosing Failures in Cyber Physical Systems