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:

This paper proposes a new network-based cyber intrusion detection system (NIDS) using multicast messages in substation automation systems (SASs). The proposed network-based intrusion detection system monitors anomalies and malicious activities of multicast messages based on IEC 61850, e.g., Generic Object Oriented Substation Event (GOOSE) and Sampled Value (SV). NIDS detects anomalies and intrusions that violate predefined security rules using a specification-based algorithm. The performance test has been conducted for different cyber intrusion scenarios (e.g., packet modification, replay and denial-of-service attacks) using a cyber security testbed. The IEEE 39-bus system model has been used for testing of the proposed intrusion detection method for simultaneous cyber attacks. The false negative ratio (FNR) is the number of misclassified abnormal packets divided by the total number of abnormal packets. The results demonstrate that the proposed NIDS achieves a low fault negative rate.

Detection of cyber intrusions using network-based multicast messages for substation automation

When an extreme weather event strikes a distribution system, the utility power may not be available for days or even weeks. As a result, a microgrid in the affected area will be operated in the islanded mode during that period. To continuously serve critical load with available generation resources, which are usually limited, load shedding actions can be performed to gradually disconnect load with low priority. This study proposes a method to obtain the dynamic load shedding strategy for an islanded microgrid with limited generation resources. First, dynamic load shedding is formulated as a stochastic optimisation problem, where the uncertainties induced by intermittent energy sources and load are incorporated. The objective is to maximise the economic performance of the microgrid. Limits on the generation resources and operational constraints are considered. Then, a model based on Markov decision process (MDP) is developed for the problem. A solution method for the MDP model is proposed to obtain the optimal load shedding strategy. Finally, numerical simulations are performed to validate the effectiveness of the proposed method. Impacts of available generation resources, uncertainties of wind power prediction, and load shedding time period on the load shedding strategy are discussed.

https://ietresearch.onlinelibrary.wiley.com/doi/pdf/10.1049/iet-gtd.2015.1452

Dynamic load shedding for an islanded microgrid with limited generation resources

Recent large-scale blackouts in North America, Europe, and other countries raised great concerns over the reliability of our electric energy infrastructure and the economic impacts of blackouts. These blackouts were caused by a cascading sequence of events involving line outages, overloading of other lines, malfunctions of protection systems, power oscillations and voltage problems, and system separation and collapse. In this paper, common characteristics of blackouts are identified by analyzing the cascaded events of the blackouts. It is important to take appropriate control actions to alleviate overload and emergency conditions in a power system in order to avoid catastrophic power outages. This paper discusses available control procedures and emergency control systems needed to help prevent catastrophic outages. Economic losses from these blackouts in the U.S., Europe, and other countries were significant. An evaluation of the economic costs of blackouts can be used to estimate the benefits of emergency control systems that can be installed to prevent blackouts. This paper provides an overview of the assessment methods and procedures for evaluation of the economic costs of blackouts. This paper also describes the generic procedure of an event study to measure the economic impact of blackouts on the values of the firms in financial markets. Copyright © 2008 John Wiley & Sons, Ltd.

Analysis, control, and economic impact assessment of major blackout events

Cyber intrusions to substations are critical issues to a power grid, which must be defended and mitigated. Essentially, to better understand a cyber intrusion, reconnaissance activities should be modeled. Then, strategies of cyber attacker and defender can be studied, which help to identify substations vulnerable to cyber-attacks. In this paper, a successful intrusion is regarded as a probabilistic event related to reconnaissance activities. Its probability can be approximated by the Poisson distribution of the number of vulnerabilities discovered by the attacker. Furthermore, models of intrusion and defense in competition for control of the substations are proposed using Markov decision process (MDP). Key characteristics of target substation, attacker and defender are considered for determining probabilistic state transitions related to intrusion and defense actions. Thus, by solving the MDP models, the optimal strategies (action policies) of both the attacker and defender can be obtained. With these optimal strategies, the cyber security status of a substation can be evaluated within varied time frames. The case study validates the proposed models and method, including time-based strategies of the attacker and defender.

Modeling of Intrusion and Defense for Assessment of Cyber Security at Power Substations

CRAFT (customer restoration and fault testing) is a rule-based expert system capable of locating the faulted section of a power transmission line based on the status of circuit breakers an automatic switches. CRAFT has been operating online in the Puget Sound Power and Light control center since July 1988. The online operational experience is reported. Many of the developed expert systems will be maintained or modified by utility engineers. This study proposes a methodology for maintaining rule-based expert systems. The following capabilities are incorporated: detecting the relations of conflict, redundancy, etc., to maintain consistency of the rule base, tracing the reasoning process to understand the problem solving approach, and reducing the size of test cases after changes are made to the rules. The proposed method has been implemented for CRAFT. >

Chen-Ching Liu

Papers

Detection of cyber intrusions using network-based multicast messages for substation automation

Dynamic load shedding for an islanded microgrid with limited generation resources

Analysis, control, and economic impact assessment of major blackout events

Modeling of Intrusion and Defense for Assessment of Cyber Security at Power Substations

Operational experience and maintenance of an on-line expert system for customer restoration and fault testing