Advancements in Deep Neural Network (DNN) models and hardware accelerators have made edge intelligence a practical alternative to cloud-based intelligence. However, applicationspecific requirements, such as accuracy, latency, security, and privacy, as well as workload fluctuations, necessitate dynamic allocation of edge and cloud resources. To facilitate such dynamic allocation, we propose an adaptive model selection and switching framework that leverages operational performance scores. We evaluate the approach using various object classification models, demonstrating its ability to balance accuracy and inference time while ensuring scalability and efficient resource utilization.

Securing IoT-based Critical Infrastructures (CI) necessitates a cross-domain management of IT/OT systems encompassing hardware, software, data, and models along with their application scenarios. There is no feasible way to manually secure such heterogeneous, weakly-protected and physically distributed systems. In this work, we propose an adaptive security framework that uses Federated Learning (FL) for IoT data monitoring and analysis at the edge. We use Deep Neural Network (DNN) model selection and switching inside FL to address performance and security problems. We began prototyping the Edge-FL system using single board computers (a Raspberry Pi-5 cluster). We measure and compare the impacts of hardware heterogeneity. The framework aims to provide continuum of security and intelligence from IoT device to Edge to Cloud.

Motivated by real customer problems, we investigated utilization of cloud services at different layers including infrastructure (IaaS), application services (PaaS) and databases (DaaS). We found several issues such as forgetting about unused resources, bursty workloads and service dependencies causing under-utilization (a.k.a. over- provisioning) problem. Cloud advisory tools offered by the public providers either lack the fine-grained analysis needed for actionable recommendations or can’t see the correlations among services that are used by the same customers’ resource groups. We proposed an automated, near real-time advisor that utilizes historical usage data and machine learning (ML) models to recommend cost saving opportunities. We demonstrated significant cost savings averaging around 20%, which can accumulate as thousands of Dollars for large and active systems. Since our advisory models depend on time-series data, we compared several forecasting algorithms including ARIMA, LSTM and Prophet. We found LSTM model to deliver the most accurate results for our workloads.

Summary Computer aided engineering (CAE) practices improved drastically within the last decade due to ease of access to computing resources and open‐source software. However, increasing complexity of hardware and software settings and the scarcity of multiskilled personnel rendered the practice inefficient and infeasible again. In this article, we present a method for continuous performance improvement in computational engineering that combines online performance profiling with machine learning (ML). To test the viability of this method, we provide a detailed analysis for solution time estimation of finite element analysis (FEA) jobs based on multidimensional models. These models combine numerous matrix features (matrix size, density, bandwidth, etc.), solver features (direct‐iterative, preconditioning, tolerance), and hardware features (core count, virtual–physical). We repeat our analysis over different machines as well as docker containers to demonstrate applicability over different platforms. Next, we train supervised and unsupervised ML algorithms over commonly used, realistic FEA benchmarks and compare accuracy of different models. Finally, we design two new ML‐based online batch schedulers called shortest predicted time first (SPTF) and shortest cluster time first (SCTF), which are comparable in performance to the optimal, but offline shortest job first (SJF) scheduler. We find that ML‐based profiling and scheduling can reduce the average turnaround times by 2 –5 over other alternatives.

Summary In this paper, we investigate several design choices for HPC services at different layers of the cloud computing architecture to simplify and broaden its use cases. We start with the platform‐as‐a‐service (PaaS) layer and compare direct and iterative parallel linear equation solvers. We observe that several matrix properties that can be identified before starting long‐running solvers can help HPC services automatically select the amount of computing resources per job, such that the job latency is minimized and the overall job throughput is maximized. As a proof of concept, we use classical problems in structural mechanics and mesh these problems with increasing granularities leading to various matrix sizes, ie, largest having 1 billion non‐zero elements. In addition to matrix size, we take into account matrix condition numbers, preconditioning effects, and solver types and execute these finite element analysis (FEA) over an IBM HPC cluster. Next, we focus on the infrastructure‐as‐a‐service (IaaS) layer and explore HPC application performance, load isolation, and deployment issues using application containers (Docker) while also comparing them to physical and virtual machines (VM) over a public cloud.

Complex Event Processing (CEP) has become increasingly important for tracking and monitoring anomalies and trends in event streams emitted from business processes such as supply chain management to online stores in e-commerce. These monitoring applications submit complex event queries to track sequences of events that match a given pattern. While the state-of-the-art CEP systems mostly focus on the execution of flat sequence queries, we instead support the execution of nested CEP queries specified by the (NEsted Event Language) NEEL. However the iterative execution often results in the repeated recomputation of similar or even identical results for nested subexpressions as the window slides over the event stream. In this work we thus propose to optimize NEEL execution performance by caching intermediate results. In particular we design two methods of applying selective caching of intermediate results. The first is the Continuous Sliding Caching technique. The second is a further optimization of the previous technique which we call the Interval-Driven Semantic Caching. Techniques for incrementally loading, purging and exploiting the cache content are described. Our experimental study using real-world stock trades evaluates the performance of our proposed caching strategies for different query types.

Due to prevalent use of sensors and network monitoring tools, big volumes of data or “big data” today traverse the enterprise data processing pipelines in a streaming fashion. While some companies prefer to deploy their data processing infrastructures and services as private clouds, others completely outsource these services to public clouds. In either case, attempting to store the data first for subsequent analysis creates additional resource costs and unwanted delays in obtaining actionable information. As a result, enterprises increasingly employ data or event stream processing systems and further want to extend them with complex online analytic and mining capabilities. In this paper, we present implementation details for doing both correlation analysis and association rule mining (ARM) over streams. Specifically, we implement Pearson-Product Moment Correlation for analytics and Apriori & FPGrowth algorithms for stream mining inside a popular event stream processing engine called Esper. As a unique contribution, we conduct experiments and present performance results of these new tools with different tumbling and sliding time-windows over two different stream types: one for moving bus trajectories and another for web logs from a music site. We find that while tumbling windows may be more preferable for performance in certain applications, sliding windows can provide additional benefits with rule mining. We hope that our findings can shed light on the design of other cloud analytics systems.

Complex Event Processing (CEP) over event streams has become increasingly important for real-time applications ranging from healthcare to supply chain management. In such applications, arbitrarily complex sequence patterns as well as non existence of such complex situations must be detected in real time. To assure real-time responsiveness for detection of such complex pattern over high volume high-speed streams, efficient processing techniques must be designed. Unfortunately the efficient processing of complex sequence queries with negations remains a largely open problem to date. To tackle this shortcoming, we designed optimized strategies for handling nested CEP query. In this demonstration, we propose to showcase these techniques for processing and optimizing nested pattern queries on streams. In particular our demonstration showcases a platform for specifying complex nested queries, and selecting one of the alternative optimized techniques including sub-expression sharing and intermediate result caching to process them. We demonstrate the efficiency of our optimized strategies by graphically comparing the execution time of the optimized solution against that of the default processing strategy of nested CEP queries. We also demonstrate the usage of the proposed technology in several healthcare services.

Complex event processing (CEP) over event streams has become increasingly important for real-time applications ranging from health care, supply chain management to business intelligence. These monitoring applications submit complex queries to track sequences of events that match a given pattern. As these systems mature the need for increasingly complex nested sequence query support arises, while the state-of-art CEP systems mostly support the execution of flat sequence queries only. To assure real-time responsiveness and scalability for pattern detection even on huge volume high-speed streams, efficient processing techniques must be designed. In this paper, we first analyze the prevailing nested pattern query processing strategy and identify several serious shortcomings. Not only are substantial subsequences first constructed just to be subsequently discarded, but also opportunities for shared execution of nested subexpressions are overlooked. As foundation, we introduce NEEL, a CEP query language for expressing nested CEP pattern queries composed of sequence, negation, AND and OR operators. To overcome deficiencies, we design rewriting rules for pushing negation into inner subexpressions. Next, we devise a normalization procedure that employs these rules for flattening a nested complex event expression. To conserve CPU and memory consumption, we propose several strategies for efficient shared processing of groups of normalized NEEL subexpressions. These strategies include prefix caching, suffix clustering and customized “bit-marking” execution strategies. We design an optimizer to partition the set of all CEP subexpressions in a NEEL normal form into groups, each of which can then be mapped to one of our shared execution operators. Lastly, we evaluate our technologies by conducting a performance study to assess the CPU processing time using real-world stock trades data. Our results confirm that our NEEL execution in many cases performs 100 fold faster than the traditional iterative nested execution strategy for real stock market query workloads.

Event correlation engines help us find events of interest inside raw sensor data streams and help reduce the data volume, simultaneously. This paper discusses some of the challenges faced in finding event correlations over federated wireless sensor networks (WSNs) including high data volumes, uncertain or missing data, application-specific dependencies and widely varying data ranges and sampling frequencies. Analysis over real geo-tracking data of moving objects confirms some of these challenges. Federation at the data layer above the WSNs is presented as a feasible alternative.

Due to copyright restrictions, the access to the full text of this article is only available via subscription.

Many modern applications including tag based mass transit systems, RFID-based supply chain management systems and online financial feeds require special purpose event stream processing technology to analyze vast amounts of sequential multi-dimensional data available in real-time data feeds. Traditional online analytical processing (OLAP) systems are not designed for real-time pattern-based operations, while Complex Event Processing (CEP) systems are designed for sequence detection and do not support OLAP operations. We will demonstrate a novel E-Cube model that combines CEP and OLAP techniques for multi-dimensional event pattern analysis at different abstraction levels. A London transit scenario will be given to demonstrate the utility and performance of this proposed technology.

The mobile shopping assistant (MSA) is a mobile application platform to deliver real-time, in-store, and personalized services, such as personalized product offerings and in-store customer advisory support, to improve the shopping experiences of in-store customers. The service delivery network that powers the MSA involves retail stores and their business partners such as manufacturers. This paper presents the core technologies that we developed in this cross-organizational service network to support the MSA and its personalized services, with focus on service delivery, customer behavior understanding and information sharing. Our event-based techniques allow customers, stores and manufacturers to deliver and consume the services in a loosely coupled manner, thus solving a critical store-specific real-time engagement problem in a seamless way. Service response tracking enables the stores to construct a comprehensive view of a customerpsilas in-store shopping behavior. Finally, the cross-organizational authorization-based access control mechanism effectively enforces information sharing between the stores and their partners.

It is extremely hard for a global organization with services over multiple channels to capture a consistent and unified view of its data, services, and interactions. While SOA and web services are addressing integration and interoperability problems, it is painful for an operational organization with legacy systems to quickly switch to service-based methods. We need methods to combine advantages of traditional (i.e. web, desktop, or mobile) application development environments and service-based deployments.In this paper, we focus on the design and implementation of session management as a core service to support business processes and go beyond application-specific sessions and web sessions. We develop local session components for different platforms and complement them with a remote "session service" that is independent of applications and platforms. We aim to close the gap between the two worlds by combining their performance, availability and interoperability advantages.

We are constructing caching policies that have 13-20% lower miss rates than the best of twelve baseline policies over a large variety of request streams. This represents an improvement of 49–63% over Least Recently Used, the most commonly implemented policy. We achieve this not by designing a specific new policy but by using on-line Machine Learning algorithms to dynamically shift between the standard policies based on their observed miss rates. A thorough experimental evaluation of our techniques is given, as well as a discussion of what makes caching an interesting on-line learning problem.