Time-preference-based on-spot bundled cloud-service provisioning
Introduction
Internet-based real-time services have been eliciting interest among customers in recent years, owing, in part, to the timely, convenient, and cost-effective delivery of services. One such service is cloud computing1 [1]. The revenue from the worldwide public cloud market is expected to be $306.9 and $364 Billion by the end of 2021 and 2022 respectively [2]. Cloud services are gaining popularity, as many enterprises are moving their operations to the cloud. For example, Expedia Inc. has migrated 80% of its services to Amazon Cloud to execute its computation-intensive tasks [3], where Expedia requires different types of resources. Thus, to provide differentiated services, cloud companies are also offering different types of services. For example, Amazon Web Service [4] offers several types of cloud-enabled services: On-Demand, Reserve, Scheduled, Dedicated and Dedicated Host, and different spot-market variants. We focus on spot-market instances in this paper.
Spot market is an offering where the service provider's unused capacity is made available to the customers without any commitment, often at significantly lower price (sometimes 90% cheaper) as compared to On-Demand and other markets [5]. Due to such discounts, spot instances are used by organizations flexible about run-time and interruptions. For example, digital platforms such as AdRoll uses Amazon EC2 spot instances on a long-term basis for their ad-delivery to 10,000 advertisers across 100 countries; see [6] for such examples.
Spot-market works on users' bids, and if that value is greater than the current spot-price,2 the service is assigned to the customer. Customers have no control over the spot-price. Hence, in contrast to other service types, the provider can terminate the instance whenever the user's bid falls below the current spot-price [7]. Such ad hoc service terms may pose an issue for time-sensitive customers, who might get dissatisfied with such unforeseen interruptions and potentially switch to competitors. This makes cloud migration challenging. Based on an analysis of cloud industry, an earlier work by Marston et al. [8] (p. 186, 2011) suggested that: “...the broad IS research agenda in cloud computing can be divided into six main potential streams [including] cloud computing economics”. As such, in this paper, we take a business/economic perspective and consider how customer preferences must be factored-in to provision them with spot-instances. We develop a service-provisioning algorithm to maximize the provider's revenue, under three key aspects:
The first aspect of our research is bundling. A bundle specifies the relative time intervals at which a group of related cloud services are required as a package for the customer-job's execution. Often, cloud users require multiple heterogeneous resources to execute their tasks (see, for example, [[9], [10], [11], [12], [13], [14]] for works that consider bundling). As indicated by Shi et al. [15] (p. 72, 2014), task decomposition of user-jobs implies that: “A cloud computing job in practice often demands a bundle of heterogenous VM instances for its successful execution”. For example, in solving complex molecular dynamics algorithms connected with biological experiments, a user requires multiple instances of different types of cloud virtual machines (based on virtual CPU, memory, storage capacity etc.) in a particular sequence. To demand all these virtual machines for the entire time-horizon would be sub-optimal for the user. Instead, therefore, the user distributes the resource requirements across the time horizon and requests the cloud provider to allocate the resources as a bundle, so that they can plan ahead. Fig. 1 depicts a similar scenario where User 1's bundle requirement includes M1-M2-M3 at time t, and M1-M2 and M1, respectively, at one and three time-periods after t (see Fig. 13) as a bundle. Likewise, User i also submits such a bundle-request.
The second aspect of our research seeks to mitigate the time-sensitivity issue mentioned above. For this, we consider the customer's preference for task-completion time. Previous cloud-related literature has also considered time-sensitivity (e.g., [[16], [17], [18], [19]]), by looking at it from a scheduling perspective, employing scheduling rules based on job-deadlines (e.g., earliest deadline first). In contrast, we consider time-sensitivity by expanding the time-horizon of the bids (from a single period to multiple periods). Within such an expanded time-horizon, we consider the customer's time-preference (TP)4 by using a behavioral economic model; i.e., we seek the completion-time preference vis-à-vis the bid-price the customer is willing to pay (i.e., their valuation) for that preference (in general, faster deliveries mean higher bids). Thus, in cases where the provider cannot offer the service to the user immediately due to lack of cloud-resource availability, the user-specified TPs can be used to satisfy the demands starting at a succeeding time-period. For example, as shown in Fig. 1, User 1 is willing to pay 25 if the bundle is accommodated starting time-period t, but only 24 for an allocation at period t + 1; the corresponding numbers for User i are 24 and 22.
The third aspect of our research is the need for a real-time solution for spot-market cloud service provisioning. Unlike the other types of cloud-services (e.g., reservation type), wherein there is sufficient time to make decisions, the decision-making time for spot-markets is low. Despite this requirement, due to limited service availability, the provider takes a longer time to offer a requested service to the customer. In many cases, the customer does not get the resource even after waiting for a long time. From the customer's perspective, a lengthy decision time could force the customer to leave for other competitors. From the provider's perspective, the supply, demand, and prices are dynamic, and hence the allocation is relevant only if it is done quickly. Thus, the service-provisioning decision based on customer's TP must be done in a short time (less than 10 min following AWS standard—see https://aws.amazon.com/ec2/faqs/). Given the three aspects of the problem mentioned above, we aim to develop a service provisioning algorithm to maximize the cloud provider's revenue.
As we will see in Section 2, the consideration of these three aspects is not there in the literature. We look into the TP literature to incorporate customer preference, along with resource bundling. This bridges the current research gaps in the cloud-service-provisioning domain. We first develop a binary integer-programming optimization model to maximize the overall revenue of the cloud provider. However, due to the hardness of the problem (see Theorem 1), we come up with a genetic-algorithm-based meta-heuristic approach to solve the problem within the stipulated time. Finally, to test the practicality of our approach, we demonstrate some key features of the algorithm with simulated datasets based on real-life scenarios.
In this work, we make three significant contributions: (1) We develop a new way of allocating cloud resources considering customer's TPs; this approach has the potential to generate better revenue than the existing approaches (2) We incorporate service bundles along with TP into our approach, bridging the gap between behavioral economics, and the practice and research of cloud service management. (3) Our meta-heuristic approach contributes to providing a better feasible solution than what general-purpose commercial software provides within the stipulated decision-time.
We first present the related work in Section 2, followed by the model development and solution approach in 3 Model development, 4 Solution approach respectively. Next, we discuss the experimental design and results in Section 5. Section 6 provides the research implications and insights of our work. Finally, we conclude our paper in Section 7.
Section snippets
Literature review
Since the basic motivation of cloud is to provide computing resources as a utility (like electricity and water), one stream of research has focused on market design; i.e., on how customers must bid and how a provider can structure the service to ensure truthful bidding by customers [[20], [21], [22], [23], [24]]. In contrast to this stream of work, once we extract TP bids (for reasons mentioned earlier), the provisioning problem we consider lies in the post-bid phase.
To help position the
Model development
In the spot-service-management problem, a set of customers (say, 1…i) submit TP based bundle requests to the spot market based on the corresponding service availability (i. e., machine types 1…j) across all the time periods (say, 1. . t). One of the challenging aspects of the problem is that the provider needs to choose the best customers from a pool of thousands of customers within ten minutes. We first characterize the TP-based revenue function, followed by the mathematical model named TP-based
Solution approach
We first show the theoretical complexity of TPOP, and then derive rules about dominance properties of the revenue function (Section 4.1). These rules are then used to derive a customized solution approach for TPOP (Section 4.2).
Experimental design and results
To check the real-time efficacy of our algorithm (hereinafter called Algo), we conduct five experiments by varying resource availability, bundle length, time periods, machine types and population diversity. Availability is the percentage of the total user requirement that is provided to the spot-market for distribution across the time-horizon. Resource availability is a key factor in the spot-market, since provisioning would be challenging if the provider has a very small number of resources
Time-preference
The problem considered herein has roots in the TP literature [[44], [45], [46], [47],57]. However, the TP literature has not seen a service-provisioning application to the cloud literature. Even though time-sensitivity is considered important [16,18,19], a behaviorally valid TP model has not been proposed. Such an application has significance for practical innovations in dynamic pricing, wherein providers are moving towards longer allocation-durations. With a better understanding of customer's
Conclusion and future work
In recent times, cloud providers have implemented new and practical business models such spot-block and others to increase their revenue from the public cloud infrastructures. As well, researchers proposed several models for different cloud markets, targeting different set of customers who have a group of requirements and have time-sensitive/deadline specifications (e.g., Begam et al. [16], Venkateswaran and Sarkar [17], Toosi et al. [23], Püschel et al. [31], Ben-Yehuda et al. [43] and
Credit author statement
All authors contributed to various stages of the paper, including the conceptualization, model development, algorithm development, writing and review. Anik Mukherjee also designed the computer programs, testing and data collection.
Anik Mukherjee is currently an assistant professor of Information Systems at IIT Roorkee, India. He conducted this research during his time at IIT Madras as a doctoral candidate. He has various international conference publications and a journal paper in the ACM Transactions on Management Information Systems. His work on this paper was partially funded by his travel to the University of South Florida on Fulbright Fellowship. He is also the recipient of other prestigious international
References (72)
- et al.
Cloud computing research in the IS discipline: a citation/co-citation analysis
Decis. Support. Syst.
(2016) - et al.
Cloud computing - the business perspective
Decis. Support. Syst.
(2011) - et al.
Time-aware cloud service recommendation using similarity-enhanced collaborative filtering and ARIMA model
Decis. Support. Syst.
(2018) - et al.
An auction method for resource allocation in computational grids
Futur. Gener. Comput. Syst.
(2010) - et al.
Pricing strategy for cloud computing: a damaged services perspective
Decis. Support. Syst.
(2015) - et al.
Maximizing business value by optimal assignment of jobs to resources in grid computing
Eur. J. Oper. Res.
(2009) - et al.
Trading grid services - a multi-attribute combinatorial approach
Eur. J. Oper. Res.
(2008) - et al.
Revenue management for cloud computing providers: decision models for service admission control under non-probabilistic uncertainty
Eur. J. Oper. Res.
(2015) - et al.
An efficient cost optimized scheduling for spot instances in heterogeneous cloud environment
Futur. Gener. Comput. Syst.
(2018) Preference structures and negotiator behavior in electronic negotiations
Decis. Support. Syst.
(2007)
Utilizing customer satisfaction in ranking prediction for personalized cloud service selection
Decis. Support. Syst.
Non-hyperbolic time inconsistency
Games Econ. Behav.
Agent based mobile negotiation for personalized pricing of last minute theatre tickets
Expert Syst. Appl.
Improved simulated annealing based risk interaction network model for project risk response decisions
Decis. Support. Syst.
A quantitative model for disruption mitigation in a supply chain
Eur. J. Oper. Res.
A decision support model for long-term course planning
Decis. Support. Syst.
Cost-based decision-making in middleware virtualization environments
Eur. J. Oper. Res.
Cloud computing and emerging IT platforms: vision, hype, and reality for delivering computing as the 5th utility
Futur. Gener. Comput. Syst.
Real-Time tasks oriented energy-aware scheduling in virtualized clouds
IEEE Trans. Cloud Comput.
Energy-efficient adaptive resource Management for Real-Time Vehicular Cloud Services
IEEE Trans. Cloud Comput.
Pricing the cloud: Resource allocations, fairness, and revenue
Reservoir - when one cloud is not enough
Computer (Long. Beach. Calif).
A combinatorial auction mechanism for multiple resource procurement in cloud computing
IEEE Trans. Cloud Comput.
An online auction framework for dynamic resource provisioning in cloud computing
Perform. Eval. Rev.
TIMER-cloud: Time-sensitive VM provisioning in resource-constrained clouds
IEEE Trans. Cloud Comput.
Time-sensitive provisioning of bare metal compute as a cloud service, IEEE Int. Conf. Cloud Comput. CLOUD. 2019-July
Cloud workflow scheduling with on-demand and spot block instances, IEEE 21st Int. Conf. Comput. Support. Coop. Work Des
Design of a multi-unit double auction e-market
Comput. Intell.
An auction mechanism for cloud spot markets
ACM Trans. Auton. Adapt. Syst.
Cited by (5)
Towards explainable artificial intelligence through expert-augmented supervised feature selection
2024, Decision Support SystemsDomain-independent real-time service provisioning in digital platforms: Featuring bundling and customer time-preference
2023, Decision Support SystemsSpot instance similarity and substitution effect in cloud spot market
2022, Decision Support SystemsCitation Excerpt :In other words, Cheng et al. [13] do not study spot price dynamics when associated data center are not distant and they are with in a region. Further, Mukherjee et al. [10] propose a new framework for spot price auction wherein customers bid for future time periods, but they also do not consider the relationships among the prices of spot instances. Some other studies in Information Systems have studied spot market pricing from the provider's perspective [8,9,18] and lack consumers' perspective.
Exploring the Cloud Computing Implementation Drivers for Sustainable Construction Projects—A Structural Equation Modeling Approach
2022, Sustainability (Switzerland)BLMDP: A new bi-level Markov decision process approach to joint bidding and task-scheduling in cloud spot market
2022, Turkish Journal of Electrical Engineering and Computer Sciences
Anik Mukherjee is currently an assistant professor of Information Systems at IIT Roorkee, India. He conducted this research during his time at IIT Madras as a doctoral candidate. He has various international conference publications and a journal paper in the ACM Transactions on Management Information Systems. His work on this paper was partially funded by his travel to the University of South Florida on Fulbright Fellowship. He is also the recipient of other prestigious international fellowships such DAAD Master’s fellowship to Germany.
R. P. Sundarraj is currently a professor of information systems at the Indian Institute of Technology, Madras. Prior to that he was a faculty member at the University of Waterloo, Canada, and at Clark University, MA, USA. He has published widely in journals such as Mathematical Programming, European Journal of Operational Research, Decision Support Systems, and various ACM and IEEE transactions.
Kaushik Dutta is currently Muma Fellow and professor of information systems at the University of South Florida. He currently also serves as the director of the School of information Systems & Management at the Muma College of Business. Professor Dutta was previously a faculty member at the National University of Singapore. He has published in prestigious journals in the area of information systems, including European Journal of Information Systems, MIS Quarterly, INFORMS Journal on Computing, and various ACM and IEEE transactions.