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:

The California energy crisis in 2000-2001 showed what could happen to an electricity market if it did not go through a comprehensive and rigorous testing before its implementation. Due to the complexity of the market structure, strategic interaction between the participants, and the underlying physics, it is difficult to fully evaluate the implications of potential changes to market rules. This paper presents a flexible and integrative method to assess market designs through agent-based modeling. Realistic simulation scenarios are constructed for evaluation of the proposed PJM-like market power mitigation rules of the California electricity market. Simulation results show that in the absence of market power mitigation, generation company (GENCO) agents facilitated by Q-learning are able to exploit the market flaws and make significantly higher profits relative to the competitive benchmark. The incorporation of PJM-like local market power mitigation rules is shown to be effective in suppressing the exercise of market power.

Evaluation of Market Rules Using a Multi-Agent System Method

A critical function in outage management for distribution systems is to quickly detect a fault and identify the activated protective device(s). With ongoing smart grid development, numerous smart meters and fault indicators with communication capabilities provide an opportunity for accurate and efficient outage management. Using the available data, this paper proposes a new multiple-hypothesis method for identification of the faulted section on a feeder or lateral. Credibility of the multiple hypotheses is determined using the available evidence from these devices. The proposed methodology is able to handle i) multiple faults, ii) protection miscoordination, and iii) missing outage reports from smart meters and fault indicators. For each hypothesis, an optimization method based on integer programming is proposed to determine the most credible actuated protective device(s) and faulted line section(s). Simulation results based on the distribution feeders of Avista Utilities serving Pullman, WA, validate the effectiveness of the proposed approach.

Outage Management of Distribution Systems Incorporating Information From Smart Meters

This paper proposes the new concept of intelligent electronic devices (IEDs) with built-in distributed intrusion detection systems. The proposed IEDs have the capabilities to monitor and detect anomalies and abnormal behaviors of the host system of IED and IEC 61850-based messages, e.g., sampled values and generic object oriented substation event. The proposed IEDs collaborate with neighboring IEDs to make an accurate decision and find the origin of cyber attacks. The commodity embedded system has been used to verify the performance of the proposed intrusion detection system with power system protection functions of IEDs. The results show that the proposed mitigation methods work accurately and efficiently with protection functions, e.g., overcurrent and distance protections, on the embedded board.

Intelligent Electronic Devices With Collaborative Intrusion Detection Systems

As part of the smart grid development, more and more technologies are developed and deployed on the power grid to enhance the system reliability. A primary purpose of the smart grid is to significantly increase the capability of computer-based remote control and automation. As a result, the level of connectivity has become much higher, and cyber security also becomes a potential threat to the cyber-physical systems (CPSs). In this paper, a survey of the state-of-the-art is conducted on the cyber security of the power grid concerning issues of: (1) the structure of CPSs in a smart grid; (2) cyber vulnerability assessment; (3) cyber protection systems; and (4) testbeds of a CPS. At Washington State University (WSU), the Smart City Testbed (SCT) has been developed to provide a platform to test, analyze and validate defense mechanisms against potential cyber intrusions. A test case is provided in this paper to demonstrate how a testbed helps the study of cyber security and the anomaly detection system (ADS) for substations.

/pdf/cyber-physical-system-security-of-a-power-grid-state-of-the-57xrrs00m1.pdf

Cyber-Physical System Security of a Power Grid: State-of-the-Art

This paper is concerned with pricing of electricity contracts that allow flexible scheduling of the supply or demand of electric energy. The contracts are priced based on the principle of no-arbitrage. Variables of the contracts are used to determine arbitrage opportunities and the price of contracts. Pricing of flexible contracts involves a scheduling policy. By representing the spot price with an appropriate stochastic process, the scheduling policy can be found using stochastic dynamic programming. Simulation examples illustrate the tradeoffs between prices and scheduling flexibility.

Chen-Ching Liu

Papers

Evaluation of Market Rules Using a Multi-Agent System Method

Outage Management of Distribution Systems Incorporating Information From Smart Meters

Intelligent Electronic Devices With Collaborative Intrusion Detection Systems

Cyber-Physical System Security of a Power Grid: State-of-the-Art

Pricing flexible electricity contracts