Data Mining - Concepts and Techniques.

What will 5G be? What it will not be is an incremental advance on 4G. The previous four generations of cellular technology have each been a major paradigm shift that has broken backward compatibility. Indeed, 5G will need to be a paradigm shift that includes very high carrier frequencies with massive bandwidths, extreme base station and device densities, and unprecedented numbers of antennas. However, unlike the previous four generations, it will also be highly integrative: tying any new 5G air interface and spectrum together with LTE and WiFi to provide universal high-rate coverage and a seamless user experience. To support this, the core network will also have to reach unprecedented levels of flexibility and intelligence, spectrum regulation will need to be rethought and improved, and energy and cost efficiencies will become even more critical considerations. This paper discusses all of these topics, identifying key challenges for future research and preliminary 5G standardization activities, while providing a comprehensive overview of the current literature, and in particular of the papers appearing in this special issue.

What Will 5G Be

The World is Flat: A Brief History of the Twenty-First Century Thomas L. Friedman Farrar, Straus and Giroux, 2005 Thomas Friedman is a widely-acclaimed journalist, foreign affairs columnist for the New York Times, and author of four best-selling books that include From Beirut to Jerusalem (1989). His eminence as a journalist is clearly demonstrated in the way he prepared for The World is Flat. He traveled throughout the world, interviewing in depth the political and business leaders who have the most direct, hands-on knowledge of the truly incredible developments occurring in the business structures and technology of globalization. Only a journalist who moves freely at the highest levels could interview the likes of Sir John Rose, the chief executive of Rolls-Royce; Nobuyuki Idei, the chairman of Sony; Richard Koo, the chief economist for the Nomura Research Institute; Bill Gates of Microsoft; Wee Theng Tan, the president of Intel China; David Baltimore, president of Caltech; Howard Schultz, founder and chairman of Starbucks; Nandan Nilekani, CEO of Infosys in Bangalore - and many others, each of whom gave him the inside story of how, specifically, the barriers of time and space separating economies, workforces, sources of capital, and technical abilities are crumbling. The result of this unfolding story, already far along but with much farther to go, according to Friedman, is that "the world is flat." With some notable exceptions in sub-Saharan Africa and the Islamic swathe, everything is connected with everything else on a horizontal basis, with distance and erstwhile time-lags no longer mattering. Friedman describes in detail the galloping globalization that has unfolded in even so limited a time as the past five years. Under the impetus of a worldwide network of interconnectivity, the world economy is much-changed from what it was at the turn of the century a mere half-decade ago. Friedman quotes the CEO of India's Infosys: "What happened over the last [few] years is that there was a massive investment in technology, especially in the bubble era, when hundreds of millions of dollars were invested in putting broadband connectivity around the world, undersea cables," while (Friedman paraphrases him) "computers became cheaper and dispersed all over the world, and there was an explosion of software - e-mail, search engines like Google, and proprietary software that can chop up any piece of work and send one part to Boston, one part to Bangalore, and one part to Beijing...." Microprocessors today have 410 million transistors compared to the 2800 they had in 1971. And now, "wireless is what will allow you to take everything that has been digitized, made virtual and personal, and do it from anywhere." The effect on productivity is revolutionary: "It now takes Boeing eleven days to build a 737, down from twenty-eight days just a few years ago. Boeing will build the next generation of planes in three days, because all the parts are computer-designed for assembly." The most strikingly informative aspect of this book, however, is not about technology. Most especially, Friedman explores the rapidly evolving global business systems, each constantly regenerating itself to keep ahead of the others. These are systems that span the continents seeking the lowest-cost providers of everything from expert scientific and engineering work to the lowliest grunt work. Friedman points out that India produces 70,000 accounting graduates each year - and that they are willing to start at $100 a month. It is no wonder that Boeing employs 800 Russian scientists and engineers for passenger-plane design when "a U.S. aeronautical engineer costs $120 per design hour, a Russian costs about one-third of that." Friedman describes a call center in India where outbound callers sell "everything from credit cards to phone minutes," while operators taking inbound calls do "everything from tracing lost luggage for U.S. and European airline passengers to solving computer problems for confused American consumers. …

The World Is Flat: A Brief History of the Twenty-First Century

In embodiments, systems and methods may involve using a platform as disclosed herein for applications described herein where the systems and methods involve receiving a dataset in an analytic platform, the dataset including fact data and dimension data for a plurality of distinct product categories It may also involve storing the data in a flexible hierarchy, the hierarchy allowing the temporary fixing of data along a dimension and flexible querying along other dimensions of the data It may also involve pre-aggregating certain combinations of data to facilitate rapid querying, the pre-aggregation based on the nature of common queries It may also involve facilitating the presentation of a cross-category view of an analytic query of the dataset In embodiments, the temporarily fixed dimension can be rendered flexible upon an action by the user

Cross-category view of a dataset using an analytic platform

With the ever-growing complexity and dynamicity of computer systems, proactive fault management is an effective approach to enhancing availability. Online failure prediction is the key to such techniques. In contrast to classical reliability methods, online failure prediction is based on runtime monitoring and a variety of models and methods that use the current state of a system and, frequently, the past experience as well. This survey describes these methods. To capture the wide spectrum of approaches concerning this area, a taxonomy has been developed, whose different approaches are explained and major concepts are described in detail.

A survey of online failure prediction methods

Nowadays, power consumption of data centers has huge impacts on environments. Researchers are seeking to find effective solutions to make data centers reduce power consumption while keep the desired quality of service or service level objectives. Virtual Machine (VM) technology has been widely applied in data center environments due to its seminal features, including reliability, flexibility, and the ease of management. We present the GreenCloud architecture, which aims to reduce data center power consumption, while guarantee the performance from users' perspective. GreenCloud architecture enables comprehensive online-monitoring, live virtual machine migration, and VM placement optimization. To verify the efficiency and effectiveness of the proposed architecture, we take an online real-time game, Tremulous, as a VM application. Evaluation results show that we can save up to 27% of the energy when applying GreenCloud architecture.

/pdf/greencloud-a-new-architecture-for-green-data-center-44id0s4omx.pdf

GreenCloud: a new architecture for green data center

The advance in wireless Internet and mobile computing brought the booming of intelligent Location-Based Services(LBS), which can actively push location-dependent information to mobile users according to their predefined interest. The successful development of push-based LBS applications relies on the existence of a publish/subscribe middleware that can handle spatial relationship. This paper presents an efficient spatial publish/subscribe system that can serve as the middleware for intelligent LBS applications. The basic models, including spatial event model, spatial subscription model and notification model, are introduced and the over-all architecture is presented. Two kinds of spatial predicate that can meet most common requirement of intelligent location aware applications are also discussed. Furthermore, we propose a novel spatial event processing approach that dispatches the spatial subscriptions to self-positioning mobile devices. By leveraging client-side computing resource and decreasing the communication times, the server-side workload is relieved and the communication cost is reduced. Experimental results clearly demonstrate the efficiency of our approach.

http://www.eecg.utoronto.ca/debs03/papers/chen_etal_debs03.pdf

An efficient spatial publish/subscribe system for intelligent location-based services

Data warehouse and Online Analytical Processing(OLAP) play a key role in business intelligent systems. With the increasing amount of spatial data stored in business database, how to utilize these spatial information to get insight into business data from the geo-spatial point of view is becoming an important issue of data warehouse and OLAP. However, traditional data warehouse and OLAP tools can not fully exploit spatial data in coordinates because multi-dimensional spatial data does not have implicit or explicit concept hierarchy to compute pre-aggregation and materialization in data warehouse. In this paper we extend the traditional set-grouping hierarchy into multi-dimensional data space and propose to use spatial index tree as the hierarchy on spatial dimension. With spatial hierarchy, spatial data warehouse can be built accordingly. Our approach preserve the star schema in data warehouse while building the hierarchy on spatial dimension, and can be easily integrated into existing data warehouse and OLAP systems. To process spatial OLAP query in spatial data warehouse, we propose an OLAP-favored search method which can utilize the pre-aggregation result in spatial data warehouse to improve the performance of spatial OLAP queries. For generality, the algorithm is developed based on Generalized Index Searching Tree(GiST). To improve the performance of OLAP-favored search, we further introduce a heuristic search method which can provide an approximate answer to spatial OLAP query. Experiment result shows the efficiency of our method.

/pdf/spatial-hierarchy-and-olap-favored-search-in-spatial-data-1qo11a0klc.pdf

Spatial hierarchy and OLAP-favored search in spatial data warehouse

As outsourcing data centers emerge to host applications or services from many different organizations and companies, it is critical for data center owners to isolate different applications while dynamically and optimally allocate resources among them To address this problem, we propose a virtual-appliance-based autonomic resource provisioning framework for large virtualized data centers Firstly, we present the architecture of the data center with enriched autonomic features Secondly, we define a non-linear constrained optimization model for dynamic resource provisioning and present its novel analytic solution Key factors including virtualization overhead and reconfiguration delay are incorporated into the model Experimental results based on a prototype system demonstrate that system-level performance has been greatly improved by taking advantage of fine-grained server consolidation Experiments with the impact of switching delay also show the efficiency of the framework through significantly reducing provisioning time

Appliance-Based Autonomic Provisioning Framework for Virtualized Outsourcing Data Center

The foremost crucial step towards a fully automated information lifecycle management (ILM) is to differentiate information by values in an unbiased manner and understand how values change over time. This paper presents an information valuation approach that quantifies the value of a given piece of information based on its usage over time. Our case study based on several real world NFS file server traces collected from Harvard University shows that such a model is simple, effective, and tangible since it relies on measurable metrics and observable facts. It captures the changing nature of the file value throughout their lifecycles, reflects the value differences among different files, and hence allows one to compare and classify files. More importantly, through additional analysis of the model outputs one can gain new insights into files, e.g., what files are most valuable and when. We show that files in different value classes exhibit different characteristics and can be characterized by unique sets of attributes. By devising algorithms to extract such attributes automatically for different classes of files, storage systems can predict what class a file would belong to early in its lifecycle, e.g., at the creation time. The file valuation, classification, and class membership prediction can then guide a wide range of new optimizations, e.g., data placement across tiered storage and data protection

/pdf/information-valuation-for-information-lifecycle-management-3j3zrrjigg.pdf

Ying Chen

Papers

GreenCloud: a new architecture for green data center

An efficient spatial publish/subscribe system for intelligent location-based services

Spatial hierarchy and OLAP-favored search in spatial data warehouse

Appliance-Based Autonomic Provisioning Framework for Virtualized Outsourcing Data Center

Information Valuation for Information Lifecycle Management