The issue of smog in smart cities (SCs) poses serious health risks due to the rising concentrations of air pollutants (APs), including particulate matter, carbon, and sulfur. Their complex and dynamic behavior makes data-driven analysis challenging. Thus, accurate source identification and forecasting of those APs are vital for assessing psychotic disorder risks in hospitalized patients. To address this, a model namedPsych-Airhas been proposed. The proposedPsych-Airmodel employs federated learning (FL) with a customized multivariate bidirectional GRU (BGRU) architecture featuring cross-variable gated attention and parallel temporal encoders. Unlike conventional FL schemes,Psych-Airincorporates heterogeneity-aware and pollutant-sensitive federated optimization, enabling stable and communication-efficient learning across non-IID smart city environments. It also models pollutant and meteorological time series as an interdependent tensor stream, with dynamic gating and synchronized bidirectional states capturing pollutant-specific patterns. A shared fusion layer learns spatiotemporal signatures predictive of psychotic disorder onset while operating securely in a decentralized environment.Psych-Aireffectively isolates latent triggers from noisy environmental data, achieving clinically relevant forecasting. FL-based BGRU identifies key pollutant sources, accounting for 46% of Air Quality Index impact in SCs. The model outperforms traditional ML, DL, and FL methods by 20%, 15%, and 10%, respectively, and supports the assessment of psychotic disorders through statistical analysis. Additionally, Psych-Air promotes sustainable, energy-efficient smart cities by reducing annual costs and CO emissions, proving adaptable across various urban settings.

Function-as-a-service (FaaS) is a popular serverless computing paradigm for event-driven functions that elastically scale on public clouds. FaaS workflows (e.g.,AWS Step FunctionsandAzure Durable Functions), are composed from FaaS functions (e.g., AWS Lambda and Azure Functions) to build practical applications. But, the complex interactions between functions in the workflow and limited visibility into the internals of proprietary FaaS platforms are major impediments to analyzing a FaaS workflow's performance. While several works characterize FaaS platforms to derive such insights, or offer FaaS Workflow benchmarks, there is a lack of a principled of FaaS workflow platforms, which have unique scaling, performance and costing behavior influenced by the platform design, dataflow and workloads. In this article, we perform extensive evaluations of three popular FaaS workflow platforms from AWS and Azure, running 25 micro-benchmark and application workflows over$139k$invocations. Our detailed analysis confirms some conventional wisdom but also uncovers unique insights on the function execution, workflow orchestration, inter-function interactions, cold-start scaling and monetary costs. Our observations help developers better configure and program these platforms, set performance and scalability expectations, and identify research gaps on enhancing the platforms.

Functions-as-a-Service (FaaS) is a widely used serverless computing abstraction that helps developers build applications using event-driven, stateless functions that execute on the cloud. Commercial FaaS platforms such as AWS Lambda and Azure Functions offer elastic auto-scaling and invocation-level billing to ease operations. Applications are often composed as a dataflow of FaaS functions that are orchestrated by FaaS workflow platforms such as AWS Step Functions or Azure Durable Functions. However, the proprietary nature of FaaS platforms on public clouds means that their internals are less understood. While benchmarks to characterize FaaS platforms exist, none are available for a principled evaluation of FaaS workflow platforms. Further, they are less configurable and often limited to simple workloads and a single cloud provider. We address this limitation by proposing XFBench, an end-to-end automated benchmarking framework for FaaS workflows that works across clouds, and an accompanying function, workflow, and workload suite. The user provides a generic definition of the workflow and workload for benchmarking, and XFBench automatically deploys the workflows across multiple cloud platforms, generates client requests, and profiles the execution. We validate XFBench with realistic workflows and workloads on AWS and Azure platforms in different global regions to offer early insights into understanding the inter-function communication, function execution time, and cold start scaling.

Internet Clouds are essentially service factories that offer various networked services through different service models, viz., Infrastructure, Platform, Software, and Functions as a Service. Meeting the desired service level objectives (SLOs) while ensuring efficient resource utilization requires significant efforts to provision the associated cloud resources correctly and on time. Therefore, one of the critical issues for any cloud service provider is resource configuration management. On one end, i.e., from the cloud operator's perspective, resource management affects overall resource utilization and efficiency. In contrast, from the cloud user/customer perspective, resource configuration affects the performance, cost, and offered SLOs. However, the state-of-the-art solutions for finding the configurations are limited to a single component or handle static workloads. Further, these solutions are computationally expensive and introduce profiling overhead, limiting scalability. Therefore, we propose COUNSEL, a deep reinforcement learning-based framework to handle the dynamic workloads and efficiently manage the configurations of an arbitrary multi-component service. We evaluate COUNSEL with three initial policies: over-provisioning, under-provisioning, and expert provisioning. In all the cases, COUNSEL eliminates the profiling overhead and achieves the average reward between 20 - 60% without violating the SLOs and budget constraints. Moreover, the inference time of COUNSEL has a constant time complexity.

The currently trending paradigms of edge and fog computing attempt to provide services close to the end user, to meet the demands of latency-sensitive applications and to limit bandwidth consumption in the network core. One open issue is the pricing of edge and fog resources. Current pricing schemes are usually oligopolistic and not fair. In this work, we propose DMC, a marketplace that can dynamically determine the fair price for arbitrary resource types and instances based on supply and demand existing at that period. Unlike the state-of-the-art solutions, DMC performs integral allocation of resources and thereby avoids the unbounded integrality gap. Additionally, DMC provides differential pricing among instances to allow varying prices based on the perceived value of a resource. We evaluate DMC with both heavy and non-heavy tailed distributions to reflect diverse buying interests and the number of resources sold to demonstrate the feasibility of our solution for several realistic scenarios. We observe that (i) DMC arrives at market-clearing prices; (ii) DMC generates 10x to 100x more profit than state-of-the-art solutions, while still maximizing the Nash Social Welfare to achieve prices that are fair to both buyers and the resource providers; and (iii) the computation time for DMC does not exceed 10 seconds even in the case of 500 resource types with 500 buyers each, making it applicable for real-time use cases.

Currently, cloud computing is a primary enabler of new paradigms such as edge and fog computing. One open issue is the pricing of services or resources. Current pricing schemes are usually oligopolistic and not fair. In this work, we propose OFM, an online learning based marketplace that dynamically determines the price for arbitrary resource types based on supply and demand existing at that period. Unlike state of the art solutions, OFM can handle an arbitrary number of customers and resource types at every instance of time. It further performs integral allocation of resources and thereby avoids the unbounded integrality gap. We evaluate OFM with both real and synthetic datasets to reflect varying buying interests, the number of resources sold and market volatility to demonstrate the feasibility of our solution for several realistic scenarios. We observe that (i) OFM achieves about 9% of optimal prices and maximizes the Nash social welfare (NSW); (ii) OFM converges faster and works with different data distributions; and (iii) OFM scales for a large number of resources and buyers and computational time is in the order of microseconds, making it applicable for real-time use cases especially in edge markets.

In hybrid cloud computing, cloud users have the ability to procure resources from multiple cloud vendors, and furthermore also the option of selecting different combinations of resources. The problem of procuring a single resource from one of many cloud vendors can be modeled as a standard winner determination problem, and there are mechanisms for single item resource procurement given different QoS and pricing parameters. There however is no compatible approach that would allow cloud users to procure arbitrary bundles of resources from cloud vendors. We design the CLOUD-CABOB algorithm to solve the multiple resource procurement problem in hybrid clouds. Cloud users submit their requirements, and in turn vendors submit bids containing price, QoS and their offered sets of resources. The approach is scalable, which is necessary given that there are a large number of cloud vendors, with more continually appearing. We perform experiments for procurement cost and scalability efficacy on the CLOUD-CABOB algorithm using various standard distribution benchmarks like random, uniform, decay and CATS. Simulations using our approach with prices procured from several cloud vendors' datasets show its effectiveness at multiple resource procurement.

Virtualization helps to deploy the functionality of expensive and rigid hardware appliances on scalable virtual resources running on commodity servers. However, optimal resource provisioning for non-trivial services is still an open problem. While there have been efforts to answer the questions of when to provision additional resources in a running service, and how many resources are needed, the question of what should be provisioned has not been investigated, in particular, for complex applications or services, which consist of a set of connected components, where each component in turn potentially consists of multiple component instances (e.g., VMs or containers). Each instance of a component can be run in different flavors (i.e., number of cores or amount of memory), while the service constructed by the combination of these component configurations must satisfy the customer Service Level Objective (SLO). In this work, we offer to service providers an answer to the what to deploy question by introducing Rconf, a system that automatically chooses the optimal combination of component instances for non-trivial network services. In particular, we propose an analytical model based on robust queuing theory that is able to accurately model arbitrary components, and develop an algorithm that finds the combination of their instances, such that the overall utilization of the running instances is maximized while meeting SLO requirements.

We present a cloud resource procurement approach which not only automates the selection of an appropriate cloud vendor but also implements dynamic pricing. Three possible mechanisms are suggested for cloud resource procurement: cloud-dominant strategy incentive compatible (C-DSIC), cloud-Bayesian incentive compatible (C-BIC), and cloud optimal (C-OPT). C-DSIC is dominant strategy incentive compatible, based on the VCG mechanism, and is a low-bid Vickrey auction. C-BIC is Bayesian incentive compatible, which achieves budget balance. C-BIC does not satisfy individual rationality. In C-DSIC and C-BIC, the cloud vendor who charges the lowest cost per unit QoS is declared the winner. In C-OPT, the cloud vendor with the least virtual cost is declared the winner. C-OPT overcomes the limitations of both C-DSIC and C-BIC. C-OPT is not only Bayesian incentive compatible, but also individually rational. Our experiments indicate that the resource procurement cost decreases with increase in number of cloud vendors irrespective of the mechanisms. We also propose a procurement module for a cloud broker which can implement C-DSIC, C-BIC, or C--OPT to perform resource procurement in a cloud computing context. A cloud broker with such a procurement module enables users to automate the choice of a cloud vendor among many with diverse offerings, and is also an essential first step toward implementing dynamic pricing in the cloud.

Multiple resource procurement from several cloud vendors participating in bidding is addressed in this paper. This is done by assigning dynamic pricing for these resources. Since we consider multiple resources to be procured from several cloud vendors bidding in an auction, the problem turns out to be one of a combinatorial auction. We pre-process the user requests, analyze the auction and declare a set of vendors bidding for the auction as winners based on the Combinatorial Auction Branch on Bids (CABOB) model. Simulations using our approach with prices procured from several cloud vendors' datasets show its effectiveness in multiple resource procurement in the realm of cloud computing.