Serverless Cloud Research Articles

Towards GPU-enabled serverless cloud edge platforms for accelerating HEVC video coding

Multimedia streaming has become integral to modern living, reshaping entertainment consumption, information access, and global engagement. The ascent of cloud computing, particularly serverless architectures, plays a pivotal role in this transformation, offering dynamic resource allocation, parallel execution, and automatic scaling-especially beneficial in HTTP Adaptive Streaming (HAS) applications. This study presents an event-driven serverless cloud edge platform with graphics processing units (GPUs), managed by Knative, tailored for video encoding. Two implementations of the High Efficiency Video Coding (HEVC) codec have been encapsulated in the functions: HEVC NVENC (Nvidia Encoder), that uses GPU acceleration, and x265 that only uses CPUs. Experiments focused on measuring the impact of replica requested resources on cold start, scalability and resource consumption with different allocated resources on slim and fat virtual machines (VMs). The best results are obtained when four slim replicas of the functions are deployed on a fat VM with a 8.4% reduction in encoding time for x265 and a 15.2% improvement for HEVC NVENC compared with other deployment scenarios. Comparatively, HEVC NVENC encoding is 8.3 times faster than x265. In multiresolution scenarios, GPU encoding drastically reduces segment encoding time by a factor of 12.4 between non-GPU and GPU-accelerated. These findings are important for live streaming applications where low latency is critical at all stages of the streaming process.

Extending the Capacity of IoT Devices with Serverless Services for a Face Detection Application: A practical evaluation

IoT systems have limitations and challenges in many ways, such as performance, energy consumption, memory footprint and data storage. One possible solution to minimize these limitations is to integrate IoT devices with the serverless cloud computing model. In this context, this work aims to analyze the integration of these two technologies to determine if it can help overcome the limitations of IoT devices, most notably energy consumption and performance. A face detection application was adapted to run on an IoT device and the AWS Serverless Lambda service. Through experimentation, some metrics like latency, execution time and energy consumption were collected to evaluate the impact of serverless technology on the scope of IoT systems development. Results show that serverless technology is superior to the IoT device used in terms of performance, but it is directly related to the quality of the network connection to which the device is connected. Serverless technology can also be very useful when power supply to an IoT device is an issue, as these devices are usually battery-connected and have limited power source.

NeuronBridge: an intuitive web application for neuronal morphology search across large data sets

BackgroundNeuroscience research in Drosophila is benefiting from large-scale connectomics efforts using electron microscopy (EM) to reveal all the neurons in a brain and their connections. To exploit this knowledge base, researchers relate a connectome’s structure to neuronal function, often by studying individual neuron cell types. Vast libraries of fly driver lines expressing fluorescent reporter genes in sets of neurons have been created and imaged using confocal light microscopy (LM), enabling the targeting of neurons for experimentation. However, creating a fly line for driving gene expression within a single neuron found in an EM connectome remains a challenge, as it typically requires identifying a pair of driver lines where only the neuron of interest is expressed in both. This task and other emerging scientific workflows require finding similar neurons across large data sets imaged using different modalities.ResultsHere, we present NeuronBridge, a web application for easily and rapidly finding putative morphological matches between large data sets of neurons imaged using different modalities. We describe the functionality and construction of the NeuronBridge service, including its user-friendly graphical user interface (GUI), extensible data model, serverless cloud architecture, and massively parallel image search engine.ConclusionsNeuronBridge fills a critical gap in the Drosophila research workflow and is used by hundreds of neuroscience researchers around the world. We offer our software code, open APIs, and processed data sets for integration and reuse, and provide the application as a service at http://neuronbridge.janelia.org.

Leveraging public cloud infrastructure for real-time connected vehicle speed advisory at a signalized corridor

In this study, we developed a real-time connected vehicle (CV) speed advisory application that uses public cloud services and tested it on a simulated signalized corridor for different roadway traffic conditions. First, we developed a scalable serverless cloud computing architecture leveraging public cloud services offered by Amazon Web Services (AWS) to support the requirements of a real-time CV application. Second, we developed an optimization-based real-time CV speed advisory algorithm by taking a modular design approach, which makes the application automatically scalable and deployable in the cloud using the serverless architecture. Third, we developed a cloud-in-the-loop simulation testbed using AWS and an open-source microscopic roadway traffic simulator called Simulation of Urban Mobility (SUMO). Our analyses based on different roadway traffic conditions showed that the serverless CV speed advisory application meets the latency requirement of real-time CV mobility applications. Besides, our serverless CV speed advisory application reduced the average stopped delay (by 77%) and the aggregated risk of collision (by 21%) at the signalized intersections of a corridor. These prove the feasibility as well as the efficacy of utilizing public cloud infrastructure to implement real-time roadway traffic management applications in a CV environment.

Pattern-based serverless data processing pipelines for Function-as-a-Service orchestration systems

The serverless cloud computing execution model presents an opportunity for implementing data processing pipelines in a cost efficient manner with minimum or no consideration about managing their operational aspects. In doing so, however, a major concern that emerges is the adoption of provider-specific languages required for orchestrating serverless functions and supporting services into the higher order logic of pipelines. As a result, the vendor lock-in problem inherent to cloud computing becomes further intensified. In this work we propose an approach to mitigate this issue through the adoption and adaptation of well-known patterns from the literature as the means for modeling the pipeline logic. By providing mappings from these patterns to vendor-specific orchestration language constructs we allow for efficient realization of provider-agnostic pipeline models as provider-specific executable workflows. An industrial case study provides evidence towards the suitability of our proposal for practical purposes.

SMSE: A serverless platform for multimedia cloud systems

SummaryAlong with the rise of domain‐specific computing (ASICs hardware) and domain‐specific programming languages, we envision that the next step is the emergence of domain‐specific cloud platforms. Considering multimedia streaming as one of the most trendy applications in the IT industry, the goal of this study is to develop serverless multimedia streaming engine (SMSE), the first domain‐specific serverless platform for multimedia streaming. SMSE democratizes multimedia service development via enabling content providers (or even end‐users) to rapidly develop their desired functionalities on their multimedia contents. Upon developing SMSE, the next goal of this study is to deal with its efficiency challenges and develop a function container provisioning method that can efficiently utilize cloud resources and improve the users' quality of service. In particular, we develop a dynamic method that provisions durable or ephemeral containers depending on the spatiotemporal and data‐dependency characteristics of the functions. Evaluating the prototype implementation of SMSE under real‐world settings demonstrates its capability to reduce both the containerization overhead, and the makespan time of serving multimedia processing functions (by up to 30%) in compare to the function provision methods that are being used in the general‐purpose serverless cloud systems.

Challenges and Opportunities in Sustainable Serverless Computing

Serverless computing has rapidly emerged as a popular deployment model. However, its energy and carbon implications are unclear and require exploration. This paper takes a look at the fundamental distinguishing attributes of serverless functions, and shows how some of them make energy-efficiency challenging. The programming model and deployment requirements of serverless functions makes them terribly energy inefficient---consuming more than 15× energy compared to conventional web services. On the bright side, FaaS is still actively expanding, and there is also an opportunity for rethinking FaaS resource management and deployment models, and make carbon efficiency a primary consideration. We present a few such techniques: moving functions to energy-friendly locations in distributed edge clouds; machine learning based modeling and control; and function-level demand response that combines ideas from approximate computing. Together, these represent a possible path forward to making serverless cloud computing sustainable.

Security computing resource allocation based on deep reinforcement learning in serverless multi-cloud edge computing

Handling computationally intensive tasks is challenging for user devices (UDs) with limited computing resources. Serverless cloud edge computing solves this problem and reduces maintenance and management. Its crucial function is to allocate computing resources reasonably. However, linking multiple computing resource nodes to perform computing resource allocation and ensure data security is a significant challenge. This study proposes an approach based on action-constrained deep reinforcement learning (DRL) to allocate computing resources securely. First, we consider a model of a serverless multi-cloud edge computing network with multiple computing resource nodes that possess various attribute characteristics. Then, we design a security mechanism to guarantee data security. Afterward, we formalize the network model and objectives and further transform them into a modeling process known as the Markov decision process. Finally, we propose DRL based on action constraints to provide an optimal resource allocation scheduling policy. Simulation results demonstrate that our approach can reduce system costs and improve working performance compared with the comparison schemes.

Enabling the Ocean Internet of Things with Renewable Marine Energy

Marine renewable energy can play an integral role in reducing the cost and complexity of collecting data from the oceans, and enhancing its exploitation. The processing and transmission of data at sea may be modelled as an `internet of things' (IoT) application. The `thing' is any offshore device which can collect and process data in-situ, while the `internet' represents the medium for transmitting data. IoT is differentiated from other internet based communication paradigms by the constraints on the system. These constraints are typically limited energy budgets and computing power, intermittent and low-bandwidth connectivity, and limited physical access. While land based IoT applications are already well served by a wide selection of hardware and software components, the needs of offshore IoT applications are not well served. Utilizing marine energy can advance the adoption of IoT at sea by providing in-situ energy generation, whilst also benefitting from the same technology. The Sustainable Energy Authority of Ireland funded `BlueBox' project aims to overcome barriers to entry for applying IoT technologies to offshore sensing by developing Ocean IoT (OIoT) hardware and software solutions. Features of the BlueBox system include modular offshore focussed hardware, no-code configuration and control of peripherals (such as sensors and actuators), duplex transmission of data using multiple media, serverless cloud server architecture and an edge computing framework. This paper presents an overview of BlueBox, tank tests for system validation of a prototype wave-energy powered ocean-observing platform, and a discussion of future applications of the technology.

Efficiency in the serverless cloud paradigm: A survey on the reusing and approximation aspects

SummaryServerless computing along with Function‐as‐a‐Service (FaaS) is forming a new computing paradigm that is anticipated to found the next generation of cloud systems. The popularity of this paradigm is due to offering a highly transparent infrastructure that enables user applications to scale in the granularity of their functions. Since these often small and single‐purpose functions are managed on shared computing resources behind the scene, a great potential for computational reuse and approximate computing emerges that if unleashed, can remarkably improve the efficiency of serverless cloud systems—both from the user's QoS and system's (energy consumption and incurred cost) perspectives. Accordingly, the goal of this survey study is to, first, unfold the internal mechanics of serverless computing and, second, explore the scope for efficiency within this paradigm via studying function reuse and approximation approaches and discussing the pros and cons of each one. Next, we outline potential future research directions within this paradigm that can either unlock new use cases or make the paradigm more efficient.

Distributed Sketching for Randomized Optimization: Exact Characterization, Concentration, and Lower Bounds

We consider distributed optimization methods for problems where forming the Hessian is computationally challenging and communication is a significant bottleneck. We leverage randomized sketches for reducing the problem dimensions as well as preserving privacy and improving straggler resilience in asynchronous distributed systems. We derive novel approximation guarantees for classical sketching methods and establish tight concentration results that serve as both upper and lower bounds on the error. We then extend our analysis to the accuracy of parameter averaging for distributed sketches. Furthermore, we develop unbiased parameter averaging methods for randomized second order optimization in regularized problems that employ sketching of the Hessian. Existing works do not take the bias of the estimators into consideration, which limits their application to massively parallel computation. We provide closed-form formulas for regularization parameters and step sizes that provably minimize the bias for sketched Newton directions. Additionally, we demonstrate the implications of our theoretical findings via large scale experiments on a serverless cloud computing platform.

Real-Time FaaS: Towards a Latency Bounded Serverless Cloud

Today, Function-as-a-Service is the most promising concept of serverless cloud computing. It makes possible for developers to focus on application development without any system management effort: FaaS ensures resource allocation, fast response time, schedulability, scalability, resiliency, and upgradability. Applications of 5G, IoT, and Industry 4.0 raise the idea to open cloud-edge computing infrastructures for time-critical applications too, i.e., there is a strong desire to pose real-time requirements for computing systems like FaaS. However, multi-node systems make real-time scheduling significantly complex since guaranteeing real-time task execution and communication is challenging even on one computing node with multi-core processors. In this paper, we present an analytical model and a heuristic partitioning scheduling algorithm suitable for real-time FaaS platforms of multi-node clusters. We show that our task scheduling heuristics could outperform existing algorithms by 55%. Furthermore, we propose three conceptual designs to enable the necessary real-time communications. We present the architecture of the envisioned real-time FaaS platform, emphasize its benefits and the requirements for the underlying network and nodes, and survey the related work that could meet these demands.

DAuth—Delegated Authorization Framework for Secured Serverless Cloud Computing

DAuth—Delegated Authorization Framework for Secured Serverless Cloud Computing

Deployment of an IoT System for Adaptive In-Situ Soundscape Augmentation

Soundscape augmentation is an emerging approach for noise mitigation by introducing additionalsounds known as "maskers" to increase indices like acoustic comfort. Traditionally, the choice of maskers is oftenpredicated on expert guidance or post-hoc analysis which can be time-consuming and sometimesarbitrary. Moreover, this often results in a static set of maskers that are inflexible to the dynamicnature of real-world acoustic environments. Overcoming the inflexibility of traditional soundscapeaugmentation is two-fold. First, given a snapshot of a soundscape, the system must be able to select anoptimal masker without human supervision. Second, the system must also be able to react to changesin the acoustic environment with near real-time latency. In this work, we harness the combinedprowess of cloud computing and internet-of-things (IoT) to allow in-situ listening and playback usingmicrocontrollers while delegating the computationally expensive inference tasks to the cloud. Inparticular, a serverless cloud architecture was used for inference, ensuring near real-time latencyand scalability without the need to provision computing resources. A working prototype of the systemis currently being deployed in a public area experiencing high traffic noise, as well as undergoingpublic evaluation for future improvements.

Penetration Testing Methodologies for Serverless Cloud Architectures

As organizations increasingly adopt serverless cloud architectures to enhance scalability and reduce operational costs, the security landscape has evolved, introducing new challenges and vulnerabilities. Serverless computing, characterized by its abstraction of infrastructure management and dynamic resource allocation, presents unique security concerns that traditional penetration testing methodologies may not adequately address. This research paper explores penetration testing methodologies specifically tailored for serverless cloud environments, aiming to identify effective strategies for evaluating and mitigating security risks in these modern architectures. The paper begins by defining serverless computing and its key characteristics, such as event-driven execution, automatic scaling, and micro-billing models. Unlike traditional server-based environments, serverless architectures often rely on Functions-as-a-Service (FaaS) and Backend-as-a-Service (BaaS) components, which can obscure the underlying infrastructure and introduce complex attack vectors. Consequently, traditional penetration testing approaches, designed for monolithic or microservices-based systems, may fall short in identifying and exploiting vulnerabilities specific to serverless environments.

Privacy-Preserving Serverless Computing Using Federated Learning for Smart Grids

The smart power grid is a critical energy infrastructure where real-time electricity usage data is collected to predict future energy requirements. The existing prediction models focus on the centralized frameworks, where the collected data from various home area networks (HANs) are forwarded to a central server. This process leads to cybersecurity threats. This article proposes a federated learning based model with privacy preservation of smart grids data using serverless cloud computing. The model considers the blockchain-enabled dew servers in each HAN for local data storage and local model training. Advanced perturbation and normalization techniques are used to reduce the inverse impact of irregular workload on the training results. The experiment conducted on benchmarks datasets demonstrates that the proposed model minimizes the computation and communication costs, attacking probability, and improves the test accuracy. Overall, the proposed model enables smart grids with robust privacy preservation and high accuracy.

A Survey on Function Level Scheduler to Minimize the Cloud Provider Resource Cost in Serverless Cloud Computing

Industry started providing the services in the form of function executions and charge the clients based on the execution time and not on the machine idle time. This change the paradigm change the way in which people started looking at cloud computing. In this paper we survey on many things which are not known to the user when they are using the platforms like AWS lambda, IBM Open Whisk and Microsoft Azure Funtions, Google cloud functions as the payment model. How the runtime is brought and saved back upon the policy of the service provider in Serverless cloud computing function as a service platforms.

MoveApps: a serverless no-code analysis platform for animal tracking data

BackgroundBio-logging and animal tracking datasets continuously grow in volume and complexity, documenting animal behaviour and ecology in unprecedented extent and detail, but greatly increasing the challenge of extracting knowledge from the data obtained. A large variety of analysis methods are being developed, many of which in effect are inaccessible to potential users, because they remain unpublished, depend on proprietary software or require significant coding skills.ResultsWe developed MoveApps, an open analysis platform for animal tracking data, to make sophisticated analytical tools accessible to a global community of movement ecologists and wildlife managers. As part of the Movebank ecosystem, MoveApps allows users to design and share workflows composed of analysis modules (Apps) that access and analyse tracking data. Users browse Apps, build workflows, customise parameters, execute analyses and access results through an intuitive web-based interface.Apps, coded in R or other programming languages, have been developed by the MoveApps team and can be contributed by anyone developing analysis code. They become available to all user of the platform. To allow long-term and cross-system reproducibility, Apps have public source code and are compiled and run in Docker containers that form the basis of a serverless cloud computing system. To support reproducible science and help contributors document and benefit from their efforts, workflows of Apps can be shared, published and archived with DOIs in the Movebank Data Repository.The platform was beta launched in spring 2021 and currently contains 49 Apps that are used by 316 registered users. We illustrate its use through two workflows that (1) provide a daily report on active tag deployments and (2) segment and map migratory movements.ConclusionsThe MoveApps platform is meant to empower the community to supply, exchange and use analysis code in an intuitive environment that allows fast and traceable results and feedback. By bringing together analytical experts developing movement analysis methods and code with those in need of tools to explore, answer questions and inform decisions based on data they collect, we intend to increase the pace of knowledge generation and integration to match the huge growth rate in bio-logging data acquisition.

R2E2

In this paper we explore the viability of path tracing massive scenes using a "supercomputer" constructed on-the-fly from thousands of small, serverless cloud computing nodes. We present R2E2 (Really Elastic Ray Engine) a scene decomposition-based parallel renderer that rapidly acquires thousands of cloud CPU cores, loads scene geometry from a pre-built scene BVH into the aggregate memory of these nodes in parallel, and performs full path traced global illumination using an inter-node messaging service designed for communicating ray data. To balance ray tracing work across many nodes, R2E2 adopts a service-oriented design that statically replicates geometry and texture data from frequently traversed scene regions onto multiple nodes based on estimates of load, and dynamically assigns ray tracing work to lightly loaded nodes holding the required data. We port pbrt's ray-scene intersection components to the R2E2 architecture, and demonstrate that scenes with up to a terabyte of geometry and texture data (where as little as 1/250th of the scene can fit on any one node) can be path traced at 4K resolution, in tens of seconds using thousands of tiny serverless nodes on the AWS Lambda platform.

Chatbot for construction firms using scalable blockchain network

Information and Communication Technologies (ICT), including multimedia tools, email services, voice-based tools, and handheld computing tools, have been extensively used for automating and digitalizing different construction processes and activities. However, these technologies are subjected to single-point attacks or failures, manipulation, and lack of privacy and traceability. This study introduces a novel information exchange and management system for construction firms based on blockchain technology and chatbots. The system leverages the characteristics of blockchain technology in terms of peer-to-peer operation mode, data integrity, structuring, and privacy, and the chatbots' merits regarding ease of use and degree of automation. The system is developed for tracking work progress in construction projects as a generic use-case using a four-step approach. First, a private blockchain network is configured for data distribution and storage. Second, a smart contract is coded for regulating data writing/reading operations. Third, a chatbot is developed for data collection and retrieval through textual conversations. Fourth, serverless cloud function and cloudant database are configured to allow the linkage between the blockchain network and the chatbot. A prototype of the system is built and applied to a case study of non-residential construction project to test and verify its capabilities. Further, the system's performance is assessed in terms of the writing and reading latencies and the storage size. The system features can be extended by embedding mathematical algorithms to simultaneously analyze data and employing Inter-Planetary File System (IPFS) to maintain visuals and large-size data.