Smart mobile devices (SMDs) can meet users' high expectations by executing computational intensive applications but they only have limited resources, including CPU, memory, battery power, and wireless medium. To tackle this limitation, partial computation offloading be used as a promising method to schedule some tasks of from resource-limited SMDs high-performance edge servers. However, it brings communication overhead issues caused bandwidth inevitably increases the latency offloaded...

The economy of scale provided by cloud attracts a growing number organizations and industrial companies to deploy their applications in data centers (CDCs) provide services users around the world. uncertainty arriving tasks makes it big challenge for private CDC cost-effectively schedule delay bounded without exceeding bounds. Unlike previous studies, this paper takes into account cost minimization problem hybrid clouds, where energy price execution public clouds both show temporal...

Edge computing is a new architecture to provide computing, storage, and networking resources for achieving the Internet of Things. It brings computation network edge in close proximity users. However, nodes have limited energy resources. Completely running tasks may cause poor performance. Cloud data centers (CDCs) rich executing tasks, but they are located places far away from CDCs lead long transmission delays large financial costs utilizing Therefore, it essential smartly offload users’...

Accurate and real-time prediction of network traffic can not only help system operators allocate resources rationally according to their actual business needs but also them assess the performance a analyze its health status. In recent years, neural networks have been proved suitable predict time series data, represented by model long short-term memory (LSTM) temporal convolutional (TCN). This article proposes novel hybrid method named SG TCN-based LSTM (ST-LSTM) for such prediction, which...

The artificial potential field approach is an efficient path planning method. However, to deal with the local-stable-point problem in complex environments, it needs modify and increases complexity of algorithm. This study combines improved black-hole reinforcement learning solve problems which are scenarios local-stable-points. used as environment a Agents automatically adapt learn how utilize basic environmental information find targets. Moreover, trained agents adopt variable environments...

A key factor of win–win cloud economy is how to trade off between the application performance from customers and profit providers. Current researches on resource allocation do not sufficiently address issues minimizing energy cost maximizing revenue for various applications running in virtualized data centers (VCDCs). This paper presents a new approach optimize VCDC based service-level agreements (SLAs) service providers customers. precise model external internal request arrival rates...

The industry of data centers is the fifth largest energy consumer in world. Distributed green (DGDCs) consume 300 billion kWh per year to provide different types heterogeneous services global users. Users around world bring revenue DGDC providers according actual quality service (QoS) their tasks. Their tasks are delivered DGDCs through multiple Internet (ISPs) with bandwidth capacities and unit price. In addition, prices power grid, wind, solar GDCs vary geographical locations. Therefore,...

As cloud computing is becoming growingly popular, consumers' tasks around the world arrive in data centers. A private provider aims to achieve profit maximization by intelligently scheduling while guaranteeing service delay bound of delay-tolerant tasks. However, aperiodicity arrival brings a challenging problem how dynamically schedule all given fact that capacity limited. Previous works usually provide an admission control refuse some Nevertheless, this will decrease throughput cloud, and...

An increasing number of enterprises have adopted cloud computing to manage their important business applications in distributed green ( DGC ) systems for low response time and high cost-effectiveness recent years. Task scheduling resource allocation DGCs gained more attention both academia industry as they are costly because energy consumption. Many factors DGCs, e.g., prices power grid, the amount express strong spatial variations. The dramatic increase arriving tasks brings a big challenge...

With their fast development and deployment, a large number of cloud services provided by distributed data centers have become the most important part Internet services. In spite numerous benefits, providers face some challenging issues, e.g., dynamic resource scaling power consumption. Workload prediction plays crucial role in addressing them. Accuracy learning are key performances. Its consistent efforts been made for improvement. This paper proposes an integrated method that combines...

Swarm intelligence in a bat algorithm (BA) provides social learning. Genetic operations for reproducing individuals genetic (GA) offer global search ability solving complex optimization problems. Their integration an opportunity improved performance. However, existing studies adopt only one operation of GA, or design hybrid algorithms that divide the overall population into multiple subpopulations evolve parallel with limited interactions only. Differing from them, this work proposes...

The infrastructure resources in distributed green cloud data centers (DGCDCs) are shared by multiple heterogeneous applications to provide flexible services global users a high-performance and low-cost way. It is highly challenging minimize the total cost of DGCDC provider market, where bandwidth prices Internet service providers (ISPs), electricity prices, availability renewable energy all vary with geographical locations. Unlike existing studies, this paper proposes spatial task scheduling...

A growing number of companies deploy their applications in green data centers (GDCs) and provide services to tasks global users. Currently, a GDC providers aim maximize profit by deploying energy facilities decreasing brown consumption. However, the temporal variation revenue, price grid, tasks' delay bounds makes it challenging for achieve maximization while strictly guaranteeing constraints all admitted tasks. Unlike existing studies, timeaware task scheduling (TATS) algorithm that...

Cost-effective task scheduling is an important operation in green infrastructure-as-a-service clouds (GICs) as the energy consumed by users' tasks drastic. The irregular arrival forces private GIC to adopt hybrid outsource some dynamic and reliable virtual machines (VMs) of public external clouds. However, temporal differences revenue, electricity prices, wind solar energy, VM running prices make it difficult dispatch all a cost-effective way while satisfying specified response time...

The significant growth in the number and types of tasks heterogeneous applications green cloud data centers (GCDCs) dramatically increases their providers' revenue from users as well energy consumption. It is a big challenge to maximize such revenue, while minimizing cost market where prices electricity, availability renewable power generation, behind-the-meter generation contract models differ among geographical sites GCDCs. A multiobjective optimization method that investigates spatial...

Mobile Devices (MDs) support various delay-sensitive and computation-intensive applications. Yet they only have limited battery energy computing resources, thereby failing to totally run all A mobile edge (MEC) paradigm has been proposed provide additional computation, storage, networking resources for MDs. Servers in MEC are often deployed both macro base stations (MBSs) small (SBSs). Thus, it is highly challenging associate resource-limited MDs them with high performance, realize partial...

Multiple heterogeneous applications concurrently run in distributed cloud data centers (CDCs) for better performance and lower cost. There is a highly challenging problem of how to minimize the total cost CDCs provider market where bandwidth energy show geographical diversity. To solve problem, this paper first proposes revenue-based workload admission control method judiciously admit requests by considering factors including priority, revenue expected response time. Then, presents...