Electric load forecasting has always been a key component of power grids. Many countries have opened up electricity markets and facilitated the participation multiple agents, which create competitive environment reduce costs to consumers. In market, multi-step short-term becomes increasingly significant for market bidding spot price calculation, but performances traditional algorithms are not robust unacceptable enough. recent years, rise deep learning gives us opportunity improve accuracy...

Dynamic provisioning is a useful technique for handling the virtualized multi-tier applications in cloud environment. Understanding performance of crucial efficient infrastructure management. In this paper, we present novel dynamic cluster-based application that employ flexible hybrid queueing model to determine number virtual machines at each tier application. We data center based on machine optimize resources provisioning. Using simulation experiments three-tier application, adopt an...

With the growth of renewable energy utilities, it is necessary to optimize system scheduling reduce operation cost and increase profit. An effective approach depends on electricity price forecasting becomes important in management control behind-the-meter storage system. In this paper, for first time, an inter-hours rolling horizon strategy proposed offer a more based high-resolution five-minute data. addition, avoid great uncertainties fluctuation, we present novel model deep learning...

In this paper, we propose a refined term frequency inversed document (TF-IDF) algorithm called TA TF-IDF to find hot terms, based on time distribution information and user attention. We also put forward method generate new terms combined which are split by the Chinese word segmentation algorithm. Then, extract news according grouping them into K-means clusters so as realize detection of topics in news. The experimental results indicated that our can effectively.

Intensive dependencies of a Java project on third-party libraries can easily lead to the presence multiple library or class versions its classpath. When this happens, JVM will load one version and shadows others. Dependency conflict (DC) issues occur when loaded fails cover required feature (e.g., method) referenced by project, thus causing runtime exceptions. However, warnings duplicate classes detected existing build tools such as Maven be benign since not all instances duplication induce...

The PyPI ecosystem has indexed millions of Python libraries to allow developers automatically download and install dependencies their projects based on the specified version constraints. Despite convenience brought by automation, constraints in can easily conflict, resulting build failures. We refer such conflicts as <u>D</u>ependency <u>C</u>onfict (DC) issues. Although DC issues are common projects, lack tool support gain a comprehensive knowledge for diagnosing root causes these In this...

Identifying influential spreaders in complex networks has a significant impact on understanding and control of spreading process networks. In this paper, we introduce new centrality index to identify network based the community structure network. The community-based (CbC) considers both number sizes communities that are directly linked by node. We discuss correlations between CbC other classical indices. Based simulations single source infection with Susceptible-Infected-Recovered (SIR)...

There is an increasing demand for indoor navigation and localization systems along with the popularity of location based services in recent years. According to past researches, Bluetooth a promising technology wireless positioning due its cost-effectiveness easy-to-deploy feature. This paper studied three typical fingerprinting-based algorithms - kNN, Neural Networks SVM. our analysis experimental results, kNN regression method proven be good candidate real-life application. Comprehensive...

In this study, we describe a system-level multiple refactoring algorithm, which can identify the move method, field, and extract class opportunities automatically according to principle of "high cohesion low coupling." The algorithm works by merging splitting related classes obtain optimal functionality distribution from system-level. Furthermore, present weighted clustering for regrouping entities in system based on merged method-level networks. Using series preprocessing steps...

Intensive use of libraries in Java projects brings potential risk dependency conflicts, which occur when a project directly or indirectly depends on multiple versions the same library class. When this happens, JVM loads one version and shadows others. Runtime exceptions can methods shadowed are referenced. Although management tools such as Maven able to give warnings conflicts is built, developers often ask for crashing stack traces before examining these warnings. It motivates us develop...

Java projects are often built on top of various third-party libraries. If multiple versions a library exist the classpath, JVM will only load one version and shadow others, which we refer to as <i>dependency conflicts</i> . This would give rise <i>semantic conflict</i> (SC) issues, if APIs referenced by project have identical method signatures but inconsistent semantics across loaded shadowed SC issues difficult for developers diagnose in practice, since understanding them typically requires...

With the increasing numbers of Web services and service users on World Wide Web, predicting QoS(Quality Service) for will greatly aid selection discovery. Due to different backgrounds experiences users, they have QoS when interacting with same service. Even two who similar some can diverging views considering other services. This paper proposes an approach predict QoS. It is based not only users' experiences, but also environment factor user input factor. First bring forwards usage...

Cloud computing focuses on delivery of reliable, secure, sustainable, dynamic and scalable resources provisioning for hosting virtualized application services in shared cloud data centers. For an appropriate mechanism, we developed a novel center architecture based virtualization mechanisms multi-tier applications, so as to reduce overheads. Meanwhile, proposed technique employed flexible hybrid queueing model determine the provision each tier services. We further meta-heuristic solutions,...

Segmentation of liver tumors plays an important role in the choice therapeutic strategies for disease and treatment monitoring. In this paper, we generalize process a level set with novel algorithm dynamic regulation to energy functional parameters. The presented method is fully automatic once tumor has been detected. First, 3D convolutional neural network dense layers classification used estimate current contour location relative boundary. Second, output CNN probabilities can dynamically...

In this paper, we propose a user profile model to describe users' preferences from multiple perspectives. Then, discuss the degree of user's for historical news, and method calculate preference weight news according reading behavior popularity news. This could construct profiles more accurately. Besides, provide dynamic recommendation, in which both short-term long-term are considered. The experimental results indicate that our can significantly improve recommendation effect.

To better control the scope of information propagation and understand its dynamic characteristics, we propose an model based on evolutionary game theory. The can simulate individual’s strategy selection in social networks when facing two pieces competitive information, whereby “competitive information” is defined as which have opposite meaning. First, a reasonable payoff function designed for individuals pairwise interaction. Second, each individual selects friend it trusts. Third,...

Online fountain codes have been proven to require lower overhead and fewer feedbacks than growth for successful decoding. In an attempt improve the intermediate symbol recovery rate, authors propose sending a number of degree‐1 input symbols prior build‐up phase based on simple application probability theory. addition, during completion phase, received encoded with three neighbouring white (un‐decoded) are retained decoding updating graph later. The performance characteristics proposed...

This paper investigates the finite-time performance control of a class switched nonlinear systems with input quantisation, where is quantised by sector-bounded quantizers. By introducing barrier Lyapunov function and hyperbolic tangent function, scheme proposed to achieve practical stability prescribed performance, new compensation constructed for effects quantisation error. Furthermore, result extended case that parameters are unknown, adaptive laws which do not require knowledge on bounds...

Residential load forecasting is important for many entities in the electricity market, but profile of single residence shows more volatilities and uncertainties. Due to difficulty producing reliable point forecasts, probabilistic becomes popular as a result catching volatility uncertainty by intervals, density, or quantiles. In this paper, we propose unified quantile regression deep neural network with time-cognition tackling challenging issue. At first, convolutional multiscale convolution...