This paper presents an efficient algorithm to solve the sleeping bandit with multiple plays problem in the context of an online recommendation system. The problem involves bounded, adversarial loss and unknown i.i.d. distributions for arm availability. The proposed algorithm extends the sleeping bandit algorithm for single arm selection and is guaranteed to achieve theoretical performance with regret upper bounded by , where k is the number of arms selected per time step, N is the total number of arms, and T is the time horizon.

A multistage approach to passive islanding detection is proposed that utilizes a decision tree (DT) like classification algorithm. The novelty of the proposed method is centered on the way in which features are passed to subsequent stages of the DT. Feature sets extracted using different sized time windows are passed to successive stages of the tree. This provides two important advantages: 1) cases that can be easily determined as either islanding or nonislanding events are flagged as soon as possible without waiting for the full feature set to become available; 2) because the algorithm allows for the use of different sized time windows, features are analyzed in time-scales that fit their natural patterns of temporal evolution. In this article, the proposed classifier is trained and tested using a database of feature vectors, obtained using PSCAD, which were designed to reflect a variety of commonly encountered events on an IEEE 34-bus distribution system. One of the key requirements for the proposed algorithm was that easy cases should be flagged as soon as possible; this property was confirmed by the observation that most events ($\approx$79%) were detected within 10–20 ms, while at the same time retaining a very high detection rate overall cases ($>\!99$%).

Rapid technological advances have led to profound changes to skills composition in the workplace. Low skilled jobs are gradually being replaced by automated systems, while there is a gaining demand for jobs which require interpersonal and technological skills. In this study, a combination of data science techniques are used to study this phenomenon. Firstly, matrix factorization and clustering methods are used to extract skills dimensions from O-NET, a database of occupations-skills matchings compiled by the US Department of Labor. A method of evaluating the performance of each of these methods is proposed and used to determine the ideal extraction procedure. Next, the relative importance of different occupations was estimated using a corpus of job advertisements collected from local job sites, which we adopt as a proxy for demand. Finally, the results of this analysis are used to measure shifts in the demand for the skills and abilities associated with these occupations. This procedure is applicable to any job market. However as a test of its effectiveness, it was used to study two important economic sectors in the United Arab Emirates (UAE): Oil & Gas and Banking & Finance. The findings of this study will help us to determine the jobs and skills which will be most impacted by structural and technological change, and provide recommendations to ensure that the UAE workforce is well equipped to adapt to these changes.

This paper proposes a novel semiautomatic system domain data analysis method. The method is based on the iterative acquisition and analysis of a large body of bibliometric data, generation of domain taxonomies, and creation of domain models. The method was applied on a smart grid case study through collection and analysis of more than 6000 documents. We have found that our method produces domain models of comparable quality to the traditional manually produced domain models in a more cost-effective way.

Wind energy is an important component in the renewable energy mix, but successful integration into existing grid infrastructure is a major challenge. In this context, the accurate prediction of future wind generation power is extremely valuable as it would facilitate more efficient and sustainable provision. In a previous work, we proposed a method for wind power prediction based on an ensemble of support vector regressors. While this approach was very promising, there are still many avenues for further improvement. In this paper, we present two key extensions to the existing methodology and show that these result in significant performance improvements. In the first approach, we seek to vary the parameter values for the component support vector regressors. This is done in two ways: random initialization, and using an evolutionary strategy to select appropriate parameter values. Secondly, we exploit correlations between the input features to reduce the dimensionality and noise. Again, two approaches are tested: a feature selection stage using correlation, and Principal Component Analysis (PCA), which is shown to greatly reduce computational requirements while increasing prediction accuracy. The combination of these two enhancements produces interesting improvements over the previous prediction system, and these are presented and discussed in this paper.

This paper presents a computational method that employs Natural Language Processing (NLP) and text mining techniques to support requirements engineers in extracting and modeling goals from textual documents. We developed a NLP-based goal elicitation approach within the context of KAOS goal-oriented requirements engineering method. The hierarchical relationships among goals are inferred by automatically building taxonomies from extracted goals. We use smart metering system as a case study to investigate the proposed approach. Smart metering system is an important subsystem of the next generation of power systems (smart grids). Goals are extracted by semantically parsing the grammar of goal-related phrases in abstracts of research publications. The results of this case study show that the developed approach is an effective way to model goals for complex systems, and in particular, for the research-intensive complex systems.

Some IP mobility protocols have been designed without enough thought given to the case that both ends of a communications session are mobile. With mobile IPv6 using route optimization, for example, a problem can arise when both ends are mobile and in particular when they move simultaneously. The relevance and significance of these solutions can properly be assessed only if a good understanding of probability of occurence of the problem and expected time to occurence (measuring from the start of the communications session) is available. In this paper, we therefore present new results on how this probability and expected duration vary with a number of critical variables, including time, handoff rates, and handoff latency.