Wanyuan Wang

Multiagent-Based Resource Allocation for Energy Minimization in Cloud Computing Systems

Cloud computing has emerged as a very flexible service paradigm by allowing users to require virtual machine (VM) resources on-demand and allowing cloud service providers (CSPs) to provide VM resources via a pay-as-you-go model. This paper addresses the CSPs problem of efficiently allocating VM resources to physical machines (PMs) with the aim of minimizing the energy consumption. Traditional energy-aware VM allocations either allocate VMs to PMs in a centralized manner or implement VM migrations for energy reduction without considering the migration cost in cloud computing systems. We address these two issues by introducing a decentralized multiagent (MA)-based VM allocation approach. The proposed MA works by first dispatching a cooperative agent to each PM to assist the PM in managing VM resources. Then, an auction-based VM allocation mechanism is designed for these agents to decide the allocations of VMs to PMs. Moreover, to tackle system dynamics and avoid incurring prohibitive VM migration overhead, a local negotiation-based VM consolidation mechanism is devised for the agents to exchange their assigned VMs for energy cost saving. We evaluate the efficiency of the MA approach by using both static and dynamic simulations. The static experimental results demonstrate that the MA can incur acceptable computation time to reduce system energy cost compared with traditional bin packing and genetic algorithm-based centralized approaches. In the dynamic setting, the energy cost of the MA is similar to that of benchmark global-based VM consolidation approaches, but the MA largely reduces the migration cost.

Toward Efficient Team Formation for Crowdsourcing in Noncooperative Social Networks

Crowdsourcing has become a popular service computing paradigm for requesters to integrate the ubiquitous human-intelligence services for tasks that are difficult for computers but trivial for humans. This paper focuses on crowdsourcing complex tasks by team formation in social networks (SNs) where a requester connects to a large number of workers. A good indicator of efficient team collaboration is the social connection among workers. Most previous social team formation approaches, however, either assume that the requester can maintain information of all workers and can directly communicate with them to build teams, or assume that the workers are cooperative and be willing to join the specific team built by the requester, both of which are impractical in many real situations. To this end, this paper first models each worker as a selfish entity, where the requester prefers to hire inexpensive workers that require less payment and workers prefer to join the profitable teams where they can gain high revenue. Within the noncooperative SNs, a distributed negotiation-based team formation mechanism is designed for the requester to decide which worker to hire and for the worker to decide which team to join and how much should be paid for his skill service provision. The proposed social team formation approach can always build collaborative teams by allowing team members to form a connected graph such that they can work together efficiently. Finally, we conduct a set of experiments on real dataset of workers to evaluate the effectiveness of our approach. The experimental results show that our approach can: 1) preserve considerable social welfare by comparing the benchmark centralized approaches and 2) form the profitable teams within less negotiation time by comparing the traditional distributed approaches, making our approach a more economic option for real-world applications.

A Practical Negotiation-Based Team Formation Model for Non-cooperative Social Networks

Team formation is an effective collaboration manner in social networks (SNs). Within teams, social individuals can work together to accomplish complex jobs that they are unable to perform individually. Due to its wide range of applications, team formation in SNs has been studied extensively and a number of approaches have been proposed. However, all of these proposals either build teams of individuals to accomplish jobs through a centralized manner or ignore the selfish nature of social individuals, or both. In this paper, we introduce a decentralized negotiation-based team formation model for non-cooperative SNs, where social individuals are self-interested. The proposed team formation model works by allowing the employer (i.e., Job initiator) to recruit a team of professional employees that demand small working remuneration and incur little communication overhead and allowing the employees to join the beneficial teams from which they can achieve a high financial remuneration. The simulation results show that our model achieves about 80% social welfare of the ideal centralized models on average. Moreover, compared to other conventional distributed models, our model can reduce team formation time significantly, making our model a better choice for the real-world time-sensitive applications.

Incentive Mechanism Design to Meet Task Criteria in Crowdsourcing: How to Determine Your Budget

In crowdsourcing markets, a requester announces a task and calls for contribution from potential participants. With strategic participants, the requester needs to reward the participants to introduce the incentives of participation. However, it is natural to ask whether it is worth introducing incentives if the total payment for eliciting incentives is too high. This paper addresses such a fundamental concern by designing a frugal mechanism with minimum payment used to procure the total amount of service contributions demanded. We design two mechanisms to provide the incentives of participation while minimizing the payment used by the requester. We first propose a frugal auction-based mechanism, which stimulates participants to truthfully report their information. We theoretically prove that the payment used is not more than the optimal cost (with no incentive considered) plus a bounded additive. We then design a Stackelberg-game-based mechanism, in which the requester fixes a certain total payment at the very beginning so as to encourage the participants to compete for it and participate in the task. We verify the existence of a unique Nash equilibrium (NE) and develop a novel algorithm to find the NE, as well as the optimal payment to extract the NE. Our simulation results show that the payment used in these mechanisms is close to the optimal solution with no incentive considered, while the extra payment caused by introducing truthfulness in auction-based mechanism is about twice that of the NE in Stakelberg-game-based mechanism.

Multiagent-Based Allocation of Complex Tasks in Social Networks

In many social networks (SNs), social individuals often need to work together to accomplish a complex task (e.g., software product development). In the context of SNs, due to the presence of social connections, complex task allocation must achieve satisfactory social effectiveness; in other words, each complex task should be allocated to socially close individuals to enable them to communicate and collaborate effectively. Although several approaches have been proposed to tackle this so-called social task allocation problem, they either suffer from being centralized or ignore the objective of maximizing the social effectiveness. In this paper, we present a distributed multiagent-based task allocation model by dispatching a mobile and cooperative agent to each subtask of each complex task, which also addresses the objective of social effectiveness maximization. With respect to mobility, each agent can transport itself to a suitable individual that has the relevant capability. With respect to cooperativeness, agents can cooperate with each other by forming teams and moving to a suitable individual jointly if the cooperation is beneficial. Our theoretical analyses provide provable performance guarantees of this model. We also apply this model in a set of static and dynamic network settings to investigate its effectiveness, scalability, and robustness. Through experimental results, our model is determined to be effective in improving the system load balance and social effectiveness; this model is scalable in reducing the computation time and is robust in adapting the system dynamics.

Migration Cost-Sensitive Load Balancing for Social Networked Multiagent Systems with Communities

In the past, many approaches have been devised to address the load balancing problem for social networked multiagent systems (SN-MASs). However, few of these approaches consider the migration cost incurred when migrating tasks for load balancing, moreover, current SN-MASs often consist of communities, and the migration costs of intra-community and intercommunity transfers are heterogeneous. To minimize the load imbalance of agents and to incur the least migration cost, this paper introduces a net profit-based load balancing mechanism. In this mechanism, each load balance process (i.e., migrating a task from one agent to another agent) is associated with a net profit value which depends on the benefit it gains by making a contribution to alleviating the system load unfairness and the cost of migrating the task. The agents always perform the optimal load balance process that has the maximum net profit value, thereby improving system performance, as well as reducing the migration cost. Our simulations show that our approach not only guarantees that agents can undertake fair loads but also reduces the overhead migration costs compared with the previous load balancing approaches that ignore the cost of migrating the task.

Practical POMDP-based test mechanism for quality assurance in volunteer crowdsourcing

ABSTRACT In volunteer crowdsourcing, tasks are published via an open call and completed by many workers without reward. Under the traditional volunteer crowdsourcing paradigm, workers with diverse levels of reliabilities are chosen indiscriminately; moreover, each worker’s performance may change over the time. Thus, the quality of task completions is a key concern in volunteer crowdsourcing. To improve the task completion quality (i.e. the accuracy of task answers), we adopt an adaptive test task (with a true answer) insertion approach to detect a worker’s performance dynamically, thereby ensuring that normal tasks (with unknown true answers) are assigned when this worker is currently deemed reliable via testing. To decide when to route test tasks to detect a worker’s performance or assign normal tasks to be completed in a high quality state, we proposed a Partially Observable Markov Decision Processes (POMDP) based test mechanism without any complicated parameter estimation, which is more practical for real-world volunteer crowdsourcing applications. In addition, we also designed rejection strategies to reject malicious workers and dubious answers. Experiments on real datasets demonstrate that the proposed test mechanism performs better in the accuracy of task answers, compared with benchmark methods.