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:

Energy transactions between electric power companies are commonly used to reduce operating costs. With movements toward a further de-regulated power industry, the number and importance of contracts are expected to increase. This paper proposes a new method to quickly and systematically evaluate potential contracts. A fundamental concern of contract analysis is whether or not the contract is feasible, i.e., if the terms of the contract, can be met without violating system operating constraints or prior contractual constraints. The novel features of our approach are a model of the essential components of a contract using rules and a contract consistency checking algorithm based on rule inference techniques. An example shows how the method is used to evaluate the consistency of a potential contract with existing contracts and other system constraints. The proposed method can help avoid tedious contract evaluation tasks while systematically ensuring that all constraints are met.

Consistency evaluation in an operational environment involving many transactions

In recent years, the concern over cyber security of power grids has increased significantly due to the fast growing connectivity among power system facilities. Several cyber security measures, e.g., intrusion detection systems (IDSs) and anomaly detection systems (ADSs), have been proposed to (1) mitigate unauthorized access, (2) detect anomalies, and (3) block abnormal behaviors in the communication system of substations. However, due to the lack of capability to handle coordinated cyber attacks by existing cyber security solutions, there is a need for effective methods that can detect coordinated cyber attacks. This paper proposes a new method to detect coordinated cyber attacks on power systems by identifying the relations among detected events. Examples of the relations include (1) IDS alarms, (2) geographic location of the attack, (3) criticality of substations, (4) firewall logs, and (5) attack patterns. Time Failure Propagation Graph (TFPG) and Fuzzy Cognitive Map (FCM) are used for the detection algorithms. A cyber-physical security testbed has been used to simulate the coordinated cyber attacks and validate the methods of the proposed coordinated cyber attack detection system (CCADS).

A coordinated cyber attack detection system (CCADS) for multiple substations

Existing system restoration strategies are primarily based on operators’ experience with no specific decision support tools. Restoration of interconnected grids in Europe is decentralised; restoration planning is limited to within the area of control for each national transmission system operator (TSO). Although coordination of restorative actions between TSOs is encouraged, few agreements exist. This study proposes a decision support methodology for system operators and restoration planners for restoration of interconnected grids. Solutions to optimal and coordinated utilisation of tie lines (TLs) are proposed. The proposed tool facilitates collaboration between TSOs affected by wide area blackouts. The decision support tool allows to adaptively develop restoration strategies based on system conditions, available resources and operating constraints. Optimisation algorithms are proposed to determine the optimal utilisation of TLs and/or black-start (BS) units to crank non-BS units. Optimal power flow problems are formulated for utilisation of TLs. They offer solutions for neighbouring TSOs to determine the extent to which TLs can be used without violating constraints. The proposed decision support tool is tested with IEEE 39-bus system.

Decision support for restoration of interconnected power systems using tie lines

Increasing penetration of proactive agents, including distributed energy resources (DERs) and responsive loads (RLs), in distribution systems motivates methods to incentivize market participation from demand-side resources. The complexity resulting from large-scale integration of proactive agents has challenged the viability of centrally managing grid resources in a distribution system environment and motivated decentralized frameworks to coordinate the transactions. Existing decentralized frameworks are primarily focused on designing transaction mechanisms. They neither include a formal market construct nor a computationally feasible approach for market settlement for a large volume of transactions while ensuring the security of grid operation. This paper presents a distributed computational approach for a distribution system market where the coordination framework is based on agreement on bilateral energy transactions reached by market participants. Using the proposed distributed computational method, participants play a role in determining the set of bilateral transactions that maximizes the social welfare. The distribution system operator (DSO) ensures a secure operating condition of the distribution grid by validating each transaction that is agreed upon. Under a potential violation of security constraints by a proposed bilateral transaction, the DSO runs an optimal power flow (OPF) and recommends a new set of transactions (closest to those previously proposed) while maintaining power system security. The proposed framework is validated using IEEE 123-node test system. The results confirm the feasibility of the proposed approach for distribution systems.

Chen-Ching Liu

Papers

Consistency evaluation in an operational environment involving many transactions

A coordinated cyber attack detection system (CCADS) for multiple substations

Decision support for restoration of interconnected power systems using tie lines

Bilateral Electricity Market in a Distribution System Environment

Design guidelines for object-oriented software with an EMS man-machine interface application