Thesis (M.S.)--University of Missouri--Rolla, 2007. / Vita. The entire thesis text is included in file. Title from title screen of thesis/dissertation PDF file (viewed March 26, 2008) Includes bibliographical references (p. 83-84).

Thesis (M.S.)--University of Texas at El Paso, 2008. / Title from title screen. Vita. CD-ROM. Includes bibliographical references. Also available online.

Thesis (M.S.)--West Virginia University, 1999. / Title from document title page. Document formatted into pages; contains x, 137 p. : ill., map Vita. Includes abstract. Includes bibliographical references (p. 99-107).

Thesis (M. S.)--Florida State University, 2005. / Advisor: Dr. An-I Andy Wang, Florida State University, College of Arts and Sciences, Dept. of Computer Science Title and description from dissertation home page (viewed Sept. 15, 2005). Document formatted into pages; contains xi, 71 pages. Includes bibliographical references.

Η κρυφή μνήμη αποτελεί έναν σημαντικό παράγοντα για την απόδοση του επεξεργαστή. Ταυτόχρονα όμως αποτελεί και ένα από τα δομικά μέρη πάνω στο chip στο οποίο καταναλώνεται σημαντικό κομμάτι της ισχύος. Στην παρούσα εργασία γίνεται μία ανάλυση πάνω στην κατανάλωση των διαφόρων επιπέδων της ιεαραρχίας της κρυφής μνήμη του επεξεργαστή και παρουσιάζονται ορισμένες τεχνικές που οδηγούν στην μείωση της ενώ παράλληλα διατηρείται η απόδοση του υπολογιστικού συστήματος όσο το δυνατόν πιο σταθερή. Η αποτίμηση των τεχνικών αυτών έγινε με την βοήθεια του SimpleScalar, εξομοιωτή υπερβαθμωτών αρχιτεκτονικών επεξεργαστή, και του εργαλείου CACTI της HP, το οποίο μοντελοποιεί διάφορα χαρακτηριστικά (χρόνο προσπέλασης, δυναμική κατανάλωση ισχύος κτλ.) της κρυφής και κύριας μνήμης του επεξεργαστή. / Cache memory plays an important role in the performance of the processor. Simultaneously, however, it is one of the core components of the chip which consume a significant percentage of the total power. In this thesis we present an analysis of the power dissipation of the different levels in cache memory hierarchy and we propose techniques that lead to a reduction of power consumption while maintaning the system performance. For the efficiency study of these techniques we use SimpleScalar, a superscalar architecture simulator, and CACTI, an enhanced cache access and cycle time model.

Orientador: Fernando Pinhabel Marafão / Coorientador: Wesley Angelino de Souza / Banca: Andre Augusto Ferreira / Banca: Eduardo Paciência Godoy / Resumo: Este trabalho apresenta o desenvolvimento de um medidor cognitivo de energia elétrica, enfatizando sua aplicação para avaliação da eficiência energética e consumo padrão de eletrodomésticos classificados pelo PROCEL e de acordo com a Etiqueta Nacional de Conservação de Energia. Para tal, é proposta uma metodologia de desagregação do consumo de energia que possibilita estimar o consumo individual de cada eletrodoméstico em uma residência. Os eletrodomésticos são classificados e identificados a partir de indicadores que caracterizam a operação de um equipamento, sendo calculados através das formas de onda de tensão e corrente e da Teoria de Potência Conservativa (CPT). Com isso, foi criada uma base de dados composta por indicadores de diversos eletrodomésticos para que se pudesse identificá-los a partir do algoritmo K-enésimo vizinho mais próximo (KNN). Tendo em vista o engajamento do consumidor residencial em relação aos seus hábitos de consumo, o trabalho proposto faz uso do medidor cognitivo de energia elétrica para fornecer recomendações e diagnósticos sobre os eletrodomésticos utilizados na residência. Por fim, o teste do protótipo possibilitou validar a metodologia proposta, estabelecendo um novo conceito e aplicação de medidores inteligentes de energia. / Abstract: This work presents the development of a cognitive energy meter, emphasizing its application to evaluate the energy efficiency and standard appliances consumption classified by PROCEL and according to the National Energy Efficiency Labeling. For this purpose, an energy consumption disaggregation methodology is proposed, which makes possible to estimate the individual consumption of each appliance in a house. Appliances are classified and identified by indicators that characterize the operation of an equipment, being calculated through voltage and current waveforms and by the Conservative Power Theory (CPT). Thus, a database composed of indicators of several household appliances was created so that they could be identified using the K-nth nearest neighbor (KNN) algorithm. Considering the engagement of the residential consumer in relation to their consumption habits, the proposed work makes the use of the cognitive energy meter to provide recommendations and diagnoses about the appliances used in the residence. Finally, the prototype validated the proposed methodology, establishing a new concept and application of smart energy meters. / Mestre

AN ABSTRACT OF THE THESIS OF Abdulaziz M. AlNowiser, for the Master of Science degree in Computer Science, presented on November 1, 2013, at Southern Illinois University Carbondale. TITLE: TOWARD ENERGY-EFFICIENT SCHEDULING USING WEIGHTED ROUND- ROBIN AND VM REUSE MAJOR PROFESSOR: Dr. Michelle M. Zhu In recent years, the rapid evolving Cloud Computing technologies multiply challenges such as minimizing power consumption and meeting Quality-of-Services (QoS) requirements in the presence of heavy workloads from a large number of users using shared computing resources. Powering a middle-sized data center normally consumes 80,000kW power every year and computer servers consume around .5% of the global power [1]. Statistics for 5000 production servers over a six-month period show that only 10-50% of the total capacity has been effectively used, and a large portion of the resources is actually wasted. In order to address the skyrocket energy cost from the high level resource management aspect, we propose an energy efficient job scheduling approach based on a modified version of Weighted Round Robin scheduler that incorporates VMs reuse and live VM migration without compromising the Service Level Agreement (SLA). The Weighted Round Robin scheduler can monitor the running VMs status for possible VM sharing for job consolidation or migration. In addition, the VMs utilization rate is observed to start live migration from the over-utilizing Processing Element (PE) to under-utilized PEs or to the hibernated PEs by sending WOL (Wake-On-LAN) signal to activate them. The simulation experiments are conducted under the CloudReports environment based on open source CloudSim simulator. The comparisons with other similar scheduling algorithms demonstrate that our enhanced Weighted Round Robin algorithm (EWRR) can achieve considerable better performance in terms of energy consumption and resource utilization rate.

Thesis (PhD (Electrical Engineering))--Potchefstroom University, 1993. / The domestic sector is one of the largest users of nett energy in the RSA (24%, excluding energy used for transport), but it accounts for only 14% of the electrical energy used in the RSA. There is a very strong correlation between the time of the peak of the load for the domestic sector and the time of the peak of the national load. The domestic load is the largest contributor to the peak of the national load. This makes the domestic load more important than is generally realised. Only limited research has been done about the ways in which domestic energy is used in South Africa. Developed countries, such as the United States of America, are continuously engaged in end-use load research, so they have vast data banks available on domestic end-uses of electricity. Data on domestic end-use of electricity are urgently needed especially for South Africa with its very fast growing newly urbanised sector. Since most energy sources are not replenishable, ways and means must be found to promote the wise and effective use of all forms of energy. Effective use of energy can only be promoted if the ways in which electricity is used are known. In this dissertation the electrical energy requirements of the South African domestic sector are analyzed for the present situation and for the next few decades. A model is developed to represent the electrical load. The model has subsections representing the components of the national domestic electrical load, concentrating on electrical energy for domestic water heating, with responses to factors such as: * population growth, * urbanisation, * electrification, * energy efficiency of appliances, * consumer awareness of energy conservation. The model is to be used for scenario planning of the electrical grid. The results of this study will assist to ensure effective planning of the electrical grid of South Africa into the next century.

Orientador: José Antonio Siqueira Dias / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Elétrica e de Computação / Made available in DSpace on 2018-08-17T01:41:45Z (GMT). No. of bitstreams: 1 Zambianco_JoseDouglasBertazzoni_M.pdf: 9119202 bytes, checksum: 1528fa36f62f343ceab5d63f4d9c113f (MD5) Previous issue date: 2010 / Resumo: O setor elétrico vem buscando cada vez mais a melhoria da qualidade dos serviços prestados a seus consumidores. Dessa forma, há uma necessidade de entender o consumo elétrico de cada cliente, onde o perfil individualizado pode trazer informações importantes quanto a utilização da energia elétrica, tornando possível a melhoria constante para melhor atender este consumidor. Neste trabalho, é apresentado um projeto, seu desenvolvimento e implementação de uma rede de sensores monitorando o consumo de cada ponto de uma casa, considerando tomadas, lâmpadas e chuveiros afim de trazer a porcentagem de uso de cada ponto de consumo. / Abstract: The electrical segment is always looking for better quality of services offered to customers. There is a demand of understand the consuption of electrical energy by each customer, it can bring an individualized profile that can show important informations related to the energy usage and how make it better. This works presents a project design, the development and implementation of a sensors network monitoring the power consuption of each point of a house, considering wall sockets, jack, electrical shower and lamps to take the percentage of each point usage. / Mestrado / Eletrônica, Microeletrônica e Optoeletrônica / Mestre em Engenharia Elétrica

This report looks at the modern cellular wireless network environment and the factors of energy consumption therein. The consumption of connectivity re- lated hardware is gradually becoming a larger part of the power consumption of virtually any mobile device. This report studies measurements of a mobile broadband module energy usage due to data transfer. It is found that switch- ing between technologies is still beneficial and savings are very feasible when using technologies with different traits if done correctly. Further the possibility of energy savings within a single high-bandwidth technology (3G) are assessed considering variations on response time and throughput. This is relevant as the need to handle highly dynamic loads becomes more and more important in the modern connectivity landscape. By gauging the savings available from schedul- ing link accesses and switching technology this is put in context by sampling a few common services namely Skype, Spotify and normal web browsing for their energy footprints. We will also look briefly at the background traffic generated by two common operating systems, Windows 7 and Ubuntu GNU/Linux.