Jorge Mario Cortés-Mendoza | South Ural State University (original) (raw)

Papers by Jorge Mario Cortés-Mendoza

Research paper thumbnail of Towards Mitigating Uncertainty of Data Security Breaches and Collusion in Cloud Computing

2017 28th International Workshop on Database and Expert Systems Applications (DEXA)

Research paper thumbnail of RoC Prediction for Bi-Objective Cost-QoS Optimization of Cloud VoIP Call Allocations

2017 IVth International Conference on Engineering and Telecommunication (EnT)

In this paper, we present cloud VoIP scheduling strategies to provide appropriate levels of quali... more In this paper, we present cloud VoIP scheduling strategies to provide appropriate levels of quality of service to users, and cost to VoIP service providers. This bi-objective problem is reasonable and representative for real installations and applications. We conduct comprehensive simulation on real data of sixty four strategies with dynamic prediction of the load. We show that our prediction rule that consider the number of Virtual Machines (VMs) running in the system improves the efficiency of traditional rate of change algorithm. It provides suitable quality of service and lower cost. Variations of VM startup time delays permit to evaluate the prediction rules under different scenarios and assess the robustness of all strategies.

Research paper thumbnail of Analysis of secured distributed cloud data storage based on multilevel RNS

2018 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus), 2018

Cloud data storages are functioning in the presence of the risks of confidentiality, integrity, a... more Cloud data storages are functioning in the presence of the risks of confidentiality, integrity, and availability related with the loss of information, denial of access for a long time, information leakage, conspiracy and technical failures. In this paper, we provide analysis of reliable, scalable, and confidential distributed data storage based on Multilevel Residue Number System (RNS) and Mignotte secret sharing scheme. We use real cloud providers and estimate characteristics such as the data redundancy, speed of data encoding, and decoding to cope with different user preferences. The analysis shows that the proposed storage scheme increases safety and reliability of traditional approaches and reduces data storage overheads by appropriate selection of RNS parameters.

Research paper thumbnail of Load-Aware Strategies for Cloud-Based VoIP Optimization with VM Startup Prediction

2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), 2017

In this paper, we address cloud VoIP scheduling strategies to provide appropriate levels of quali... more In this paper, we address cloud VoIP scheduling strategies to provide appropriate levels of quality of service to users, and cost to VoIP service providers. This bi-objective focus is reasonable and representative for real installations and applications. We conduct comprehensive simulation on real data of twenty three on-line non-clairvoyant scheduling strategies with fixed threshold of utilization to request VMs, and twenty strategies with dynamic prediction of the load. We show that our load-aware with predictions strategies outperform the known ones providing suitable quality of service and lower cost. The robustness of these strategies is also analyzed varying VM startup time delays to deal with realistic VoIP cloud environments.

Research paper thumbnail of Distributed Adaptive VoIP Load Balancing in Hybrid Clouds

Cloud computing as a powerful economic stimulus widely being adopted by many companies. However, ... more Cloud computing as a powerful economic stimulus widely being adopted by many companies. However, the management of cloud infrastructure is a challenging task. Reliability, security, quality of service, and cost-efficiency are important issues in these systems. They require resource optimization at multiple layers of the infrastructure and applications. The complexity of cloud computing systems makes infeasible the optimal resource allocation, especially in presence of uncertainty of very dynamic and unpredictable environment. Hence, load balancing algorithms are a fundamental part of the research in cloud computing. We formulate the problem of load balancing in distributed computer environments and review several algorithms. The goal is to understand the main characteristics of dynamic load balancing algorithms and how they can be adapted for the domain of VoIP computations on hybrid clouds. We conclude by showing how none of these works directly addresses the problem space of the c...

Research paper thumbnail of Configurable cost-quality optimization of cloud-based VoIP

Journal of Parallel and Distributed Computing

Research paper thumbnail of AC-RRNS: Anti-collusion secured data sharing scheme for cloud storage

International Journal of Approximate Reasoning

Research paper thumbnail of AR-RRNS: Configurable reliable distributed data storage systems for Internet of Things to ensure security

Future Generation Computer Systems

Research paper thumbnail of Min_c: Heterogeneous concentration policy for energy-aware scheduling of jobs with resource contention

Programming and Computer Software

Research paper thumbnail of Robust cloud VoIP scheduling under VMs startup time delay uncertainty

Proceedings of the 9th International Conference on Utility and Cloud Computing - UCC '16, 2016

In this paper, we address cloud VoIP service orchestration and scheduling to provide appropriate ... more In this paper, we address cloud VoIP service orchestration and scheduling to provide appropriate levels of quality of service to users, and performance to VoIP service providers. We consider voice quality affected by call processing, and cost contributed by billing hours for used VMs in a cloud. We believe that this biobjective focus is reasonable and representative for real installations and applications. We conduct comprehensive simulation of our calls load balancing strategies on real data and show that not all approaches provide suitable quality of service. We analyze eight on-line dynamic non-clairvoyant scheduling strategies with variations in VM startup time delays to deal with realistic VoIP cloud environments. We show that the proposed strategies outperform currently in use strategies in terms of quality of service and provider cost. The robustness of these strategies is also discussed.

Research paper thumbnail of Min_с: стратегия неоднородной концентрации задач для энергосберегающих компьютерных расписаний

Proceedings of the Institute for System Programming of the RAS, 2015

Республиканский университет, Мотневидео, Уругвай Аннотация. В этой статье мы описываем энергосбер... more Республиканский университет, Мотневидео, Уругвай Аннотация. В этой статье мы описываем энергосберегающие онлайн расписания вычислительных задач и механизмы повышения энергоэффективности, учитывая конфликты использования ресурсов. Мы предлагаем модель оптимизации и новый подход к распределению задач, принимая во внимание типы приложений и их концентрацию. Разнородные задачи, решаемые на процессорах, включают в себя приложения, интенсивно использующие процессоры, диски, устройства ввода-вывода, память, сети и т.д. Когда задачи одного типа назначаются на один и тот же ресурс, они могут создать конфликты при использовании CPU, памяти, диска или сети. Это может привести к деградации общей производительности системы и увеличению потребления энергии. Мы описываем энергетические характеристики приложений, учитывая, что выполнение различных задач по-разному влияет на потребляемую мощность за счет использования разного оборудования. Мы предлагаем нелинейную гибридную модель потребления энергии, которая учитывает потребление энергии отдельных приложений и их комбинации. Мы показываем, что умные стратегии распределения задач могут 1 Работы выполнены при финансовой поддержке Минобрнауки России (Соглашение № 02.G25.31.0061 12/02/2013).

Research paper thumbnail of VoIP Traffic Modelling Using Gaussian Mixture Models, Gaussian Processes and Interactive Particle Algorithms

2015 IEEE Globecom Workshops (GC Wkshps), 2015

The paper deals with an important problem in the Voice over IP (VoIP) domain, namely being able t... more The paper deals with an important problem in the Voice over IP (VoIP) domain, namely being able to understand and predict the structure of traffic over some given period of time. VoIP traffic has a time variant structure, e.g. due to sudden peaks, daily or weekly moving patterns of activities, which in turn makes prediction difficult. Obtaining insights about the structure and trends of traffic has important implications when dealing with the nowadays cloud-deployed VoIP services. Prediction techniques are applied to anticipate the incoming traffic, for an efficient distribution of the traffic in the system and allocation of resources. The article looks in a critical manner at a series of machine learning techniques. We namely compare and review (using real VoIP data) the results obtained when using a Gaussian Mixture Model (GMM), Gaussian Processes (GP), and an evolutionarylike Interacting Particle Systems based (sampling) algorithm. The experiments consider different setups as to verify the time variant traffic assumption.

Research paper thumbnail of Distributed VoIP Load Balancing in Cloud Computing

Cloud computing is widely being adopted by many companies because it allows to maximize the utili... more Cloud computing is widely being adopted by many companies because it allows to maximize the utilization of their resources. Unfortunately, the management of cloud infrastructure is a challenging task. Reliability, security, quality of service, and cost-efficiency are important issues in these systems, they require resource optimization at multiple layers of the infrastructure and applications. The complexity of cloud computing systems makes infeasible the optimal or near-optimal resource allocation, especially in presence of uncertainty of very dynamic and unpredictable environment. Hence, load balancing algorithms are a fundamental part of the research in cloud computing. We formulate the problem and describe several load balancing algorithms in distributed computer environments. The goal is to understand the main characteristics of load balancing algorithms and how they can be adapted for the domain of VoIP computations on federated clouds. We conclude by showing how none of these...

Research paper thumbnail of Adaptive energy efficient distributed VoIP load balancing in federated cloud infrastructure

2014 IEEE 3rd International Conference on Cloud Networking (CloudNet), 2014

Cloud computing is widely being adopted by many companies because it allows to maximize the utili... more Cloud computing is widely being adopted by many companies because it allows to maximize the utilization of resources. However, the complexity of cloud computing systems with the existence of many cloud providers makes infeasible for the end user the optimal or near-optimal resource provisioning and utilization, especially in presence of uncertainty of very dynamic and unpredictable environment. Hence, dynamic adaptive load balancing algorithms are a fundamental part of the research in cloud computing. We formulate the problem and propose an adaptive load balancing algorithm for distributed computer environments. We also discuss the energy efficiency of our solution for the domain of VoIP computations on federated clouds.

Research paper thumbnail of Generalized extremal optimization for parallel job scheduling in two levels hierarchical Grid systems

Grids are becoming almost commonplace nowadays because of the benefits shown when it is necessary... more Grids are becoming almost commonplace nowadays because of the benefits shown when it is necessary to work with a large amount of data or computing power. The initial challenges of Grid computing have been overcome to first order (running a job, transferring files, managing multiple user accounts, etc.). Researchers can now address the issues involved to improve the uses of Grid computing, one of the most studied field is job scheduling. Several techniques have been used to address the problem of scheduling. In recent years the use of heuristics inspired by nature has boomed owing the effectiveness to solve hard problems. This work presents the generalized extremal optimization heuristic (GEO) to solve parallel job scheduling problem in two levels hierarchical Grid systems. GEO heuristic is based on the extremal optimization observed in complex systems, where generational avalanches evolve an ecosystem to a critical state. The abstraction of this model has been successfully implement...

Research paper thumbnail of Distributed Adaptive VoIP Load Balancing in Hybrid Clouds

Cloud computing as a powerful economic stimulus widely being adopted by many companies. However, ... more Cloud computing as a powerful economic stimulus widely being adopted by many companies. However, the management of cloud infrastructure is a challenging task. Reliability, security, quality of service, and cost-efficiency are important issues in these systems. They
require resource optimization at multiple layers of the infrastructure and applications. The complexity of cloud computing systems makes unfeasible the optimal resource allocation, especially in presence of uncertainty of very dynamic and unpredictable environment. Hence, load balancing algorithms are a fundamental part of the research in cloud computing. We formulate the problem of load balancing in distributed computer environments and review several algorithms. The goal is to understand the main characteristics of dynamic load balancing algorithms and how they can be adapted for the domain of VoIP computations on hybrid clouds. We conclude by showing how none of these works directly addresses the problem space of the considered problem, but do provide a valuable basis for our work.

Research paper thumbnail of Heterogeneous Job Consolidation for Power Aware Scheduling with Quality of Service

In this paper, we present an energy optimization model of Cloud computing, and formulate novel en... more In this paper, we present an energy optimization model of Cloud computing, and formulate novel energy-aware resource allocation problem that provides energy-efficiency by heterogeneous job consolidation taking into account types of applications. Data centers process heterogeneous workloads that include CPU intensive, disk I/O intensive, memory intensive, network I/O intensive and other types of applications. When one type of applications creates a bottleneck and resource contention either in CPU, disk or network, it may result in degradation of the system performance and increasing energy consumption. We discuss energy characteristics of applications, and how an awareness of their types can help in intelligent allocation strategy to improve energy consumption.

Research paper thumbnail of Distributed Adaptive VoIP Load Balancing in Hybrid Clouds

NC&SC’2015 - Network Computing & Supercomputing workshop. In conjunction with RuSCDays'15 - The Russian Supercomputing Days, September 28-29, 2015, Moscow

Cloud computing as a powerful economic stimulus widely being adopted by many companies. However, ... more Cloud computing as a powerful economic stimulus widely being adopted by many companies. However, the management of cloud infrastructure is a challenging task. Reliability, security, quality of service, and cost-efficiency are important issues in these systems. They require
resource optimization at multiple layers of the infrastructure and applications. The complexity
of cloud computing systems makes infeasible the optimal resource allocation, especially in presence of uncertainty of very dynamic and unpredictable environment. Hence, load balancing algorithms are a fundamental part of the research in cloud computing. We formulate the problem of load balancing in distributed computer environments and review several algorithms. The goal is to understand the main characteristics of dynamic load balancing algorithms and how they can be adapted for the domain of VoIP computations on hybrid clouds. We conclude by showing how none of these works directly addresses the problem space of the considered problem, but do provide a valuable basis for our work

Research paper thumbnail of Heterogeneous Job Consolidation for Power Aware Scheduling with Quality of Service

NC&SC’2015 - Network Computing & Supercomputing workshop. In conjunction with RuSCDays'15 - The Russian Supercomputing Days, September 28-29, 2015, Moscow

In this paper, we present an energy optimization model of Cloud computing, and formulate novel en... more In this paper, we present an energy optimization model of Cloud computing, and formulate novel energy-aware resource allocation problem that provides energy-efficiency by heterogeneous job consolidation taking into account types of applications. Data centers process heterogeneous workloads that include CPU intensive, disk I/O intensive, memory intensive, network I/O intensive and other types of applications. When one type of applications creates a bottleneck and resource contention either in CPU, disk or network, it may result in degradation of the system performance and increasing energy consumption. We discuss energy characteristics of applications, and how an awareness of their types can help in intelligent allocation strategy to improve energy consumption.

Research paper thumbnail of Towards Mitigating Uncertainty of Data Security Breaches and Collusion in Cloud Computing

2017 28th International Workshop on Database and Expert Systems Applications (DEXA)

Research paper thumbnail of RoC Prediction for Bi-Objective Cost-QoS Optimization of Cloud VoIP Call Allocations

2017 IVth International Conference on Engineering and Telecommunication (EnT)

In this paper, we present cloud VoIP scheduling strategies to provide appropriate levels of quali... more In this paper, we present cloud VoIP scheduling strategies to provide appropriate levels of quality of service to users, and cost to VoIP service providers. This bi-objective problem is reasonable and representative for real installations and applications. We conduct comprehensive simulation on real data of sixty four strategies with dynamic prediction of the load. We show that our prediction rule that consider the number of Virtual Machines (VMs) running in the system improves the efficiency of traditional rate of change algorithm. It provides suitable quality of service and lower cost. Variations of VM startup time delays permit to evaluate the prediction rules under different scenarios and assess the robustness of all strategies.

Research paper thumbnail of Analysis of secured distributed cloud data storage based on multilevel RNS

2018 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus), 2018

Cloud data storages are functioning in the presence of the risks of confidentiality, integrity, a... more Cloud data storages are functioning in the presence of the risks of confidentiality, integrity, and availability related with the loss of information, denial of access for a long time, information leakage, conspiracy and technical failures. In this paper, we provide analysis of reliable, scalable, and confidential distributed data storage based on Multilevel Residue Number System (RNS) and Mignotte secret sharing scheme. We use real cloud providers and estimate characteristics such as the data redundancy, speed of data encoding, and decoding to cope with different user preferences. The analysis shows that the proposed storage scheme increases safety and reliability of traditional approaches and reduces data storage overheads by appropriate selection of RNS parameters.

Research paper thumbnail of Load-Aware Strategies for Cloud-Based VoIP Optimization with VM Startup Prediction

2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), 2017

In this paper, we address cloud VoIP scheduling strategies to provide appropriate levels of quali... more In this paper, we address cloud VoIP scheduling strategies to provide appropriate levels of quality of service to users, and cost to VoIP service providers. This bi-objective focus is reasonable and representative for real installations and applications. We conduct comprehensive simulation on real data of twenty three on-line non-clairvoyant scheduling strategies with fixed threshold of utilization to request VMs, and twenty strategies with dynamic prediction of the load. We show that our load-aware with predictions strategies outperform the known ones providing suitable quality of service and lower cost. The robustness of these strategies is also analyzed varying VM startup time delays to deal with realistic VoIP cloud environments.

Research paper thumbnail of Distributed Adaptive VoIP Load Balancing in Hybrid Clouds

Cloud computing as a powerful economic stimulus widely being adopted by many companies. However, ... more Cloud computing as a powerful economic stimulus widely being adopted by many companies. However, the management of cloud infrastructure is a challenging task. Reliability, security, quality of service, and cost-efficiency are important issues in these systems. They require resource optimization at multiple layers of the infrastructure and applications. The complexity of cloud computing systems makes infeasible the optimal resource allocation, especially in presence of uncertainty of very dynamic and unpredictable environment. Hence, load balancing algorithms are a fundamental part of the research in cloud computing. We formulate the problem of load balancing in distributed computer environments and review several algorithms. The goal is to understand the main characteristics of dynamic load balancing algorithms and how they can be adapted for the domain of VoIP computations on hybrid clouds. We conclude by showing how none of these works directly addresses the problem space of the c...

Research paper thumbnail of Configurable cost-quality optimization of cloud-based VoIP

Journal of Parallel and Distributed Computing

Research paper thumbnail of AC-RRNS: Anti-collusion secured data sharing scheme for cloud storage

International Journal of Approximate Reasoning

Research paper thumbnail of AR-RRNS: Configurable reliable distributed data storage systems for Internet of Things to ensure security

Future Generation Computer Systems

Research paper thumbnail of Min_c: Heterogeneous concentration policy for energy-aware scheduling of jobs with resource contention

Programming and Computer Software

Research paper thumbnail of Robust cloud VoIP scheduling under VMs startup time delay uncertainty

Proceedings of the 9th International Conference on Utility and Cloud Computing - UCC '16, 2016

In this paper, we address cloud VoIP service orchestration and scheduling to provide appropriate ... more In this paper, we address cloud VoIP service orchestration and scheduling to provide appropriate levels of quality of service to users, and performance to VoIP service providers. We consider voice quality affected by call processing, and cost contributed by billing hours for used VMs in a cloud. We believe that this biobjective focus is reasonable and representative for real installations and applications. We conduct comprehensive simulation of our calls load balancing strategies on real data and show that not all approaches provide suitable quality of service. We analyze eight on-line dynamic non-clairvoyant scheduling strategies with variations in VM startup time delays to deal with realistic VoIP cloud environments. We show that the proposed strategies outperform currently in use strategies in terms of quality of service and provider cost. The robustness of these strategies is also discussed.

Research paper thumbnail of Min_с: стратегия неоднородной концентрации задач для энергосберегающих компьютерных расписаний

Proceedings of the Institute for System Programming of the RAS, 2015

Республиканский университет, Мотневидео, Уругвай Аннотация. В этой статье мы описываем энергосбер... more Республиканский университет, Мотневидео, Уругвай Аннотация. В этой статье мы описываем энергосберегающие онлайн расписания вычислительных задач и механизмы повышения энергоэффективности, учитывая конфликты использования ресурсов. Мы предлагаем модель оптимизации и новый подход к распределению задач, принимая во внимание типы приложений и их концентрацию. Разнородные задачи, решаемые на процессорах, включают в себя приложения, интенсивно использующие процессоры, диски, устройства ввода-вывода, память, сети и т.д. Когда задачи одного типа назначаются на один и тот же ресурс, они могут создать конфликты при использовании CPU, памяти, диска или сети. Это может привести к деградации общей производительности системы и увеличению потребления энергии. Мы описываем энергетические характеристики приложений, учитывая, что выполнение различных задач по-разному влияет на потребляемую мощность за счет использования разного оборудования. Мы предлагаем нелинейную гибридную модель потребления энергии, которая учитывает потребление энергии отдельных приложений и их комбинации. Мы показываем, что умные стратегии распределения задач могут 1 Работы выполнены при финансовой поддержке Минобрнауки России (Соглашение № 02.G25.31.0061 12/02/2013).

Research paper thumbnail of VoIP Traffic Modelling Using Gaussian Mixture Models, Gaussian Processes and Interactive Particle Algorithms

2015 IEEE Globecom Workshops (GC Wkshps), 2015

The paper deals with an important problem in the Voice over IP (VoIP) domain, namely being able t... more The paper deals with an important problem in the Voice over IP (VoIP) domain, namely being able to understand and predict the structure of traffic over some given period of time. VoIP traffic has a time variant structure, e.g. due to sudden peaks, daily or weekly moving patterns of activities, which in turn makes prediction difficult. Obtaining insights about the structure and trends of traffic has important implications when dealing with the nowadays cloud-deployed VoIP services. Prediction techniques are applied to anticipate the incoming traffic, for an efficient distribution of the traffic in the system and allocation of resources. The article looks in a critical manner at a series of machine learning techniques. We namely compare and review (using real VoIP data) the results obtained when using a Gaussian Mixture Model (GMM), Gaussian Processes (GP), and an evolutionarylike Interacting Particle Systems based (sampling) algorithm. The experiments consider different setups as to verify the time variant traffic assumption.

Research paper thumbnail of Distributed VoIP Load Balancing in Cloud Computing

Cloud computing is widely being adopted by many companies because it allows to maximize the utili... more Cloud computing is widely being adopted by many companies because it allows to maximize the utilization of their resources. Unfortunately, the management of cloud infrastructure is a challenging task. Reliability, security, quality of service, and cost-efficiency are important issues in these systems, they require resource optimization at multiple layers of the infrastructure and applications. The complexity of cloud computing systems makes infeasible the optimal or near-optimal resource allocation, especially in presence of uncertainty of very dynamic and unpredictable environment. Hence, load balancing algorithms are a fundamental part of the research in cloud computing. We formulate the problem and describe several load balancing algorithms in distributed computer environments. The goal is to understand the main characteristics of load balancing algorithms and how they can be adapted for the domain of VoIP computations on federated clouds. We conclude by showing how none of these...

Research paper thumbnail of Adaptive energy efficient distributed VoIP load balancing in federated cloud infrastructure

2014 IEEE 3rd International Conference on Cloud Networking (CloudNet), 2014

Cloud computing is widely being adopted by many companies because it allows to maximize the utili... more Cloud computing is widely being adopted by many companies because it allows to maximize the utilization of resources. However, the complexity of cloud computing systems with the existence of many cloud providers makes infeasible for the end user the optimal or near-optimal resource provisioning and utilization, especially in presence of uncertainty of very dynamic and unpredictable environment. Hence, dynamic adaptive load balancing algorithms are a fundamental part of the research in cloud computing. We formulate the problem and propose an adaptive load balancing algorithm for distributed computer environments. We also discuss the energy efficiency of our solution for the domain of VoIP computations on federated clouds.

Research paper thumbnail of Generalized extremal optimization for parallel job scheduling in two levels hierarchical Grid systems

Grids are becoming almost commonplace nowadays because of the benefits shown when it is necessary... more Grids are becoming almost commonplace nowadays because of the benefits shown when it is necessary to work with a large amount of data or computing power. The initial challenges of Grid computing have been overcome to first order (running a job, transferring files, managing multiple user accounts, etc.). Researchers can now address the issues involved to improve the uses of Grid computing, one of the most studied field is job scheduling. Several techniques have been used to address the problem of scheduling. In recent years the use of heuristics inspired by nature has boomed owing the effectiveness to solve hard problems. This work presents the generalized extremal optimization heuristic (GEO) to solve parallel job scheduling problem in two levels hierarchical Grid systems. GEO heuristic is based on the extremal optimization observed in complex systems, where generational avalanches evolve an ecosystem to a critical state. The abstraction of this model has been successfully implement...

Research paper thumbnail of Distributed Adaptive VoIP Load Balancing in Hybrid Clouds

Cloud computing as a powerful economic stimulus widely being adopted by many companies. However, ... more Cloud computing as a powerful economic stimulus widely being adopted by many companies. However, the management of cloud infrastructure is a challenging task. Reliability, security, quality of service, and cost-efficiency are important issues in these systems. They
require resource optimization at multiple layers of the infrastructure and applications. The complexity of cloud computing systems makes unfeasible the optimal resource allocation, especially in presence of uncertainty of very dynamic and unpredictable environment. Hence, load balancing algorithms are a fundamental part of the research in cloud computing. We formulate the problem of load balancing in distributed computer environments and review several algorithms. The goal is to understand the main characteristics of dynamic load balancing algorithms and how they can be adapted for the domain of VoIP computations on hybrid clouds. We conclude by showing how none of these works directly addresses the problem space of the considered problem, but do provide a valuable basis for our work.

Research paper thumbnail of Heterogeneous Job Consolidation for Power Aware Scheduling with Quality of Service

In this paper, we present an energy optimization model of Cloud computing, and formulate novel en... more In this paper, we present an energy optimization model of Cloud computing, and formulate novel energy-aware resource allocation problem that provides energy-efficiency by heterogeneous job consolidation taking into account types of applications. Data centers process heterogeneous workloads that include CPU intensive, disk I/O intensive, memory intensive, network I/O intensive and other types of applications. When one type of applications creates a bottleneck and resource contention either in CPU, disk or network, it may result in degradation of the system performance and increasing energy consumption. We discuss energy characteristics of applications, and how an awareness of their types can help in intelligent allocation strategy to improve energy consumption.

Research paper thumbnail of Distributed Adaptive VoIP Load Balancing in Hybrid Clouds

NC&SC’2015 - Network Computing & Supercomputing workshop. In conjunction with RuSCDays'15 - The Russian Supercomputing Days, September 28-29, 2015, Moscow

Cloud computing as a powerful economic stimulus widely being adopted by many companies. However, ... more Cloud computing as a powerful economic stimulus widely being adopted by many companies. However, the management of cloud infrastructure is a challenging task. Reliability, security, quality of service, and cost-efficiency are important issues in these systems. They require
resource optimization at multiple layers of the infrastructure and applications. The complexity
of cloud computing systems makes infeasible the optimal resource allocation, especially in presence of uncertainty of very dynamic and unpredictable environment. Hence, load balancing algorithms are a fundamental part of the research in cloud computing. We formulate the problem of load balancing in distributed computer environments and review several algorithms. The goal is to understand the main characteristics of dynamic load balancing algorithms and how they can be adapted for the domain of VoIP computations on hybrid clouds. We conclude by showing how none of these works directly addresses the problem space of the considered problem, but do provide a valuable basis for our work

Research paper thumbnail of Heterogeneous Job Consolidation for Power Aware Scheduling with Quality of Service

NC&SC’2015 - Network Computing & Supercomputing workshop. In conjunction with RuSCDays'15 - The Russian Supercomputing Days, September 28-29, 2015, Moscow

In this paper, we present an energy optimization model of Cloud computing, and formulate novel en... more In this paper, we present an energy optimization model of Cloud computing, and formulate novel energy-aware resource allocation problem that provides energy-efficiency by heterogeneous job consolidation taking into account types of applications. Data centers process heterogeneous workloads that include CPU intensive, disk I/O intensive, memory intensive, network I/O intensive and other types of applications. When one type of applications creates a bottleneck and resource contention either in CPU, disk or network, it may result in degradation of the system performance and increasing energy consumption. We discuss energy characteristics of applications, and how an awareness of their types can help in intelligent allocation strategy to improve energy consumption.