Dynamic adaptive streaming over HTTP (DASH) has been widely used in video streaming recently. In DASH, the client downloads video chunks in order from a server. The rate adaptation function at the video client enhances the user?s quality-of-experience (QoE) by choosing a suitable quality level for each video chunk to download based on the network condition. Today networks such as content delivery networks, edge caching networks, contentcentric networks, etc. usually replicate video contents on multiple cache nodes. We study video streaming from multiple sources in this work. In multi-source streaming, video chunks may arrive out of order due to different conditions of the network paths. Hence, to guarantee a high QoE, the video client needs not only rate adaptation, but also chunk scheduling. Reinforcement learning (RL) has emerged as the state-of-the-art control method in various fields in recent years. This paper proposes two algorithms for streaming from multiple sources: RL-based adaptation with greedy scheduling (RLAGS) and RL-based adaptation and scheduling (RLAS). We also build a simulation environment for training and evaluation. The efficiency of the proposed algorithms is proved via extensive simulations with real-trace data.

Dynamic adaptive streaming over HTTP (DASH) is widely used in video streaming recently. With DASH, a video is stored in multiple equal-playing-time chunks with different quality levels. Video chunks are in-order delivered from a single source over a path in traditional DASH. The adaptation function in video player chooses a suitable quality level to request depending on current network status for each video chunk. In modern networks such as content delivery networks, edge caching, content-centric networks, etc., popular video contents are replicated at multiple cache nodes. Utilizing multiple sources for video streaming is investigated in this paper. We propose a reinforcement learning based algorithm, called RAMS, for rate adaptation in multi-source video streaming. The proposed algorithm outperforms the other notable adaptation methods.

In this survey, we review the existing game-theoretic approaches for cyber security and privacy issues, categorizing their application into two classes, security and privacy. To show how game theory is utilized in cyberspace security and privacy, we select research regarding three main applications: cyber-physical security, communication security, and privacy. We present game models, features, and solutions of the selected works and describe their advantages and limitations from design to implementation of the defense mechanisms. We also identify some emerging trends and topics for future research. This survey not only demonstrates how to employ game-theoretic approaches to security and privacy but also encourages researchers to employ game theory to establish a comprehensive understanding of emerging security and privacy problems in cyberspace and potential solutions.

Workload consolidation is an efficient approach to reduce the power consumption of datacenters, meanwhile load balancing can reduce the datacenter's user delay. Despite complexities of 1) the coupling between consolidation and load balancing methods for server allocation, and 2) the heterogeneity of server configurations, we address the joint consolidation and service-aware load balancing problem to minimize the operation cost of datacenters. We first formulate the joint optimization problem, which is NP-hard. We then solve this problem using the Gibbs sampling method. Furthermore, to improve the computation of our approach, we propose the JCL algorithm that combines Gibbs sampling and the ADMM method for parallel and distributed calculations. Simulation results also validate that our method not only reduces the power consumption and delay cost, but also balances the workload in heterogeneous servers.

This paper studies price competition in a heterogeneous cloud market formed by public providers and a cloud broker, all of which are also known as cloud service providers (CSPs). We formulate the price competition between CSPs as a two-stage noncooperative game. In stage I, in which CSPs set their service prices to maximize their revenues, we model the pricing game using the noncooperative static game. We provide sufficient conditions for the existence and uniqueness of Nash equilibrium prices, which can be obtained using an iterative algorithm. The convergence properties of the iterative algorithm are characterized using the contract mapping theorem. In stage II, given the prices set by CSPs, cloud users can select the services that provide them the best payoff in terms of performance (i.e., delay) and price. We apply an evolutionary game to study the evolution and dynamic behavior of cloud users. Furthermore, we use the Wardrop equilibrium and replicator dynamics to determine the equilibrium and its convergence properties of the service selection game. To attract users to the equilibrium, we implement the service selection algorithms using population evolution and reinforcement learning approaches. Numerical results illustrate that our game models can provide comprehensive understanding of the heterogeneous CSPs market and service selection in cloud computing.

We take the first step to study the price competition in a heterogeneous market cloud computing formed by public provider and cloud broker, all of which are also known as cloud service providers. We formulate a price competition between cloud broker and public provider as a two-stage non-cooperative game. In stage one, where cloud service providers set their service prices to maximize their revenue, we use the Nash equilibrium concept to study the equilibria for the price setting game. Cloud users can select the services (from the cloud broker or public provider) that provide them the best payoff in terms of performance (i.e., delay) and price. To that end, cloud users can adapt their service selection behavior by observing the variations in price and quality of service offered by the different cloud service providers. For the service selection game of cloud users in stage two, we use the evolutionary game model to study the evolution and the dynamic behavior of cloud users. Furthermore, the Wardrop equilibrium and replicator dynamics is applied to determine the equilibrium and its convergence properties of the service selection game. Numerical results illustrate that our game model captures the main factors behind the heterogeneous market cloud pricing and service selection, thus represents a promising framework for the design and understanding of the heterogeneous market cloud computing.

Demand response programs have been considered critical for power grid reliability and efficiency. Especially, the demand response of datacenters has recently received encouraging efforts due to huge demands and flexible power control knobs of datacenters. However, most current efforts focus on owner-operated datacenters, omitting another critical segment of datacenter business: multitenant colocation. In colocation datacenters, while there exist multiple tenants who manage their own servers, the colocation operator only provides facilities such as cooling, reliable power, and network connectivity. Therefore, colocation has a unique feature that challenges any attempts to design a demand response program: uncoordinated power management among tenants. To tackle this challenge, two incentive mechanisms are proposed to coordinate tenant power consumption for demand response under two different scenarios. First, in the case of economic demand response where the operator can adjust an elastic energy reduction target, we show that there is an interaction between the operator and tenant strategies, where each side maximizes its own benefit. Hence, we apply a two-stage Stackelberg game to analyze this scenario and derive this game's equilibria. However, computing these equilibria can be intractable with exhaustive search; therefore, we propose an algorithm to find the Stackelberg equilibria with linear complexity. Second, in the case of emergency demand response where a fixed energy reduction target must be fulfilled, we devise two incentive schemes with the distributed algorithms that can achieve the same optimal social cost. While the first algorithm is based on the dual-decomposition method that is suitable for nonstrategic tenants, the second one is designed for strategic tenants to achieve a unique Nash equilibrium of a bidding game. Finally, trace-based simulations are also provided to illustrate the efficacy of our proposed incentive schemes.

In this paper, we consider two critical issues in data centers: load balancing and server consolidation. We propose a live consolidation method, which identifies an optimal strategy of hosting a new virtual machine (VM). Our algorithm finds the optimal allocation scheme to host a VM in term of load balancing, reducing the migration cost, and mitigating resource redundancy. Based on queueing and optimization theory, we model the allocation resource in data centers and analyze how to choose the location for each VM, and also minimize the number of active servers. The live consolidate algorithm exploits the distribution VM process and determines the optimal active server set. The numerical analysis demonstrates that our algorithm is able to consolidate the system lively. By using a real dataset, our simulation results show that the optimal distribution probability vector can allocate a new VM into a appropriate server to improve the resource utilization and the energy efficiency.

In the area of cloud infrastructure environment, the management tool to monitor and control the cloud resources is the important factor that can drive the cost benefit of the cloud vendors. But most these tools are bundled within the high cost commercial platforms and are optimized to run on desktop computers. With the vision that Mobile Cloud Computing will be the future technology paradigm that dominates the IT industry, we want to create a cloud management tool that is open source, fast, lightweight and mobile friendly. We take the initial steps by implementing our framework using several popular technologies such as RESTful, Java Message Service, JSON, and we call it “High performance and Lightweight Mobile Cloud Infrastructure Monitor and Benchmark Service” or HiLiCloud. The initial testings show competitive evaluation results.

In heterogeneous networks (HetNets), low power smallcells, i.e., Wifi, can be offered an economic incentive in order to offload traffic from high-power macrocell, which is usually overloaded. This becomes important in order to maintain efficient operation of the network and generate benefit of tradeoff between macrocell and smallcells. The benefit to smallcells comes from the economic incentive offered by macrocell and the benefit to macrocell is achieved by reducing the load and saving spectrum. However, two important challenges are faced in this cooperation: 1) How much economic incentive can be offered by macrocell, and 2) How much offloading traffic volumes can be admitted by the smallcells. In this paper, we propose a novel game based approach for data offloading scheme to determine the amount of economic incentive a macrocell should offer to smallcells and to determine how much traffic each smallcell should admit from the macrocell. In our proposal, a two-stage non-cooperative Stackelberg game theory is applied to optimize the strategies of both macrocell and smallcells in order to maximize their utilities.

We consider the sum-rate optimization problem with power control for uplink transmission in a heterogeneous network (HetNet) consisting of a macrocell and multiple femtocells. The considered problem includes the HetNet's crucial constraints of both cross-tier interference protection and user QoS in terms of outage probability and average delay. We transform the original nonconvex problem into a convex problem and develop a distributed algorithm that can attain the global optimal transmit power values. This algorithm, however, has heavy network overheads, which may lead to increased energy consumption for femtocell user equipment. We propose a new practical near-optimal distributed algorithm that eliminates these network overheads. Numerical results show that the schemes have nearly identical performance.

Demand response of datacenters recently has received increasing efforts due to huge demands and flexible power control knobs. However, very few works focus on a critical segment of datacenter business: multi-tenant colocation. In colocation datacenters, while there exist multiple tenants who manger their own servers, the colocation operator only provides other facilities such as cooling, reliable power, and network connectivity. Therefore, colocation has a unique challenge for the demand response: uncoordinated power management among tenants. To tackle this challenge, we study how to coordinate tentants for economic demand response. We show that there is an interaction between the operator and tenants' strategies, where each side maximizes its own benefit. Hence, we apply a two-stage Stackelberg game to analyze this scenario and derive this game's equilibria. Finally, trace-based simulations are also provided to illustrate the efficacy of our proposed incentive schemes.

Large-scale Internet applications, such as content distribution networks, are deployed in a geographically distributed manner and emit massive amounts of carbon footprint at the data center. To provide uniform low access latencies, Cisco has introduced Fog computing as a new paradigm which can transform the network edge into a distributed computing infrastructure for applications. Fog nodes are geographically distributed and the deployment size at each location reflects the regional demand for the application. Thus, we need to control the fraction of user traffic to data center to maximize the social welfare. In this paper, we consider the emerging problem of joint resource allocation and minimizing carbon footprint problem for video streaming service in Fog computing. To solve the largescale optimization, we develop a distributed algorithm based on the proximal algorithm and alternating direction method of multipliers (ADMM). The numerical results show that our algorithm converges to near optimum within fifteen iterations, and is insensitive to step sizes.

In this paper, we consider the emerging problem of joint resource allocation and minimizing carbon footprint problem for video streaming service in Fog computing. To solve the large-scale optimization, we develop a distributed algorithm based on the proximal algorithm. The numerical results show that our algorithm converges to near optimum within fifteen iterations, and is insensitive to step sizes.

Multimedia cloud, as a strict QoS requirement cloud paradigm, addresses how cloud can effectively process multimedia services for multimedia applications. In this paper, we optimize resource allocation for multimedia cloud based on queuing model. Numerical results demonstrate that the proposed optimal allocation scheme can optimally utilize the cloud resources to achieve a maximum revenue.

Power control is critical for femtocell networks that allow spectrum sharing among Macrocell and Femtocell. In this paper, we derive an optimal power control strategy toward reducing the CO2 emissions and maximize total throughput under both the probability of dropping a packet due to buffer overflow constraints at the Femtocell user equipment (FUE) and the interference constraints to the Macrocell base station (MBS) for uplink transmission. We use linear programming to solve the CO2 emissions minimization problem. For maximizing the total throughput of FUEs, we propose a distributed power control algorithms by employing geometry convex tool. Numerical results are used to validate the analysis and demonstrate a high degree of accuracy for the derived expressions. Results indicate that the performance of the FUEs depends on not only the interference constraint of the MBS but also the delay constraint of the FUEs.

In this paper, we optimize resource allocation for multimedia cloud based on queuing model. Specifically, we optimize the resource allocation in both single multimedia service provider (MSP) scenario and multiple MSPs scenario. In each scenario, we formulate and solve the MSPs' revenue maximization problem under eviction probability constraint of users. Numerical results demonstrate that the proposed optimal allocation scheme can optimally utilize the cloud resources to achieve a maximum revenue.

In this paper, we consider the cooperation among users in heterogeneous wireless networks (HetNets). Some users in HetNets will play a role as the relays for a macro user when the macro user cannot connect to the macro base stations or femto base stations directly. In this scenario, the macro user tries to find a best relay user in a set of candidate relays to maximize its utility function. In return, each relay user gives a pricing-based strategy to the macro user to maximize the relay user s utility function. This problem is formulated as a Stackelberg game in static environment. Moreover, with stochastic environment we model as a restless bandit problem to maximize the utility functions of the relay users and the macro user in a long-term. Simulation results illustrate the efficiency of our proposal.

Vehicular Ad hoc Network (VANET) is developed for more driving efficicency, comfort and safety. The IEEE 802.11p/WAVE is a standard intended to support wireless access in VANETs. In this paper, we propose an analytical model to evaluate the performance of the IEEE 802.11p based MAC for VANETs under non-saturation condition through the packet delivery ratio, the average delay of emergency message and the throughput of service message. The 2-D Markov model is used to model two access categories in the IEEE 802.11p. The analytical model is validated by the extensive simulation, and it shows the impact of different parameters on the performance of network.