Serverless vs. Containerized Workloads: Comparative Performance and Cost under Bursty Telecom Traffic

We introduce EMARS, an efficient resource management system for serverless cloud computing frameworks with the goal to enhance resource (focus on memory) allocation among containers. We have built our prototype on top of an open-source serverless platform, OpenLambda. It is based upon application workloads and serverless functions' memory needs. As a background motivation we analyzed the latencies and memory requirements of functions running on AWS lambda. The memory limits also lead to variations in number of containers spawned on OpenLambda. We use memory limit settings to propose a model of predictive efficient memory management.

Serverless computing is a recent paradigm to program the cloud. It allows to execute user-defined functions at scale, on demand, and in a pay-per-use manner. This paper reports on adapting the Unix shell for serverless. Our software, called the serverless shell (sshell), runs shell scripts on a serverless platform much like with a regular computer. It permits to reuse an existing code base while benefiting from the massive power of serverless and paying only for the resources used. sshell is built around a small set of components that includes a new inter-process communication layer for serverless. We evaluate it in AWS Lambda using several microbenchmarks and a large-scale application. Our results show that sshell achieves comparable or better performance than a high-end server. Moreover, it can be faster and more cost-efficient than a cluster-based solution to mine large datasets.

In the era of pervasive digital transformation, the need for real-time data processing and intelligent analytics has become paramount, especially in critical sectors like healthcare. This paper presents a novel serverless cloud-based architecture designed for efficient sensor data analytics in real-time healthcare environments. The proposed model integrates modular components including API gateways, serverless functions, stream buffering, and analytical engines to ensure scalability, fault tolerance, and cost-efficiency with higher throughput. Nature-inspired optimization technique is included to expedite data search in the server, for the same a comparative study has been conducted on a hybrid model of Spider Monkey Optimization (SMO) and Ant Colony Optimization (ACO) it is used to augment data discovery in uninformed search environments. Experimental evaluations using AWS Lambda, S3, and API Gateway reveal the proposed model's superior performance in execution time, accuracy, and scalability under varying load conditions. This architecture demonstrates significant promise for healthcare applications requiring intelligent, responsive, and resource-efficient cloud solutions.

Serverless functions [6, 9, 13, 14], like AWS Lambda [3] or Google Cloud Functions [7], are new techniques for running short-lived workloads over a cloud, which are particularly preferred by users for their easy deployment, fine-grained billing and automatic scaling. Unlike traditional cloud offerings such as VMs and containers, these functions are stateless, where each function execution starts with a fresh state of memory, disk, and other resources. A multi-tenant serverless cloud platform has two primary components, a gateway controlled by the cloud service provider (CSP) and the user functions which are users' programs. A typical serverless function execution is stateless and involves broadly the following steps: (1) User request is received by the gateway, (2) Gateway executes the function and passes the request arguments, (3) The function performs necessary computation, (4) Optionally, it can call other functions through the gateway or access external Database, and (5) It returns the result to the user.

New computational architectures, such as multi-core processors and graphics processing units (GPUs), pose challenges to application developers. Although in the case of general-purpose GPU programming, environments and toolkits such as CUDA and OpenCL have simplified application development, different ways of thinking about memory access, storage, and program execution are required. This paper presents a strategy for implementing a specific signal processing technique for blind-source separation: infomax independent component analysis (ICA). Common linear algebra operations are mapped to a low cost programmable graphics card using the OpenCL programming toolkit. Because many components of ICA are inherently parallel, ICA computations can be accelerated by low cost parallel hardware. Experimental results on simulated and speech signals indicate that efficiency gains and scalability are achievable through general-purpose GPU implementation, and suggest that important applications in telecommunications, speech processing, and biomedical signal analysis can benefit from these new architectures. The utilization of low cost GPUs for programming may potentially facilitate real-time applications of previously offline algorithms.

In this study, a number of modified Smith predictor (SP)-based fractional order control strategies are investigated experimentally on a thermal process. Controller design methods and tuning strategies are elaborated step by step. Further, control strategies are discussed in relation to design specifications, control cost, implementation issues, and operating modes encountered in practice. Performance comparison is presented via several illustrations and numerical measures. Particular attention is paid to the tracking precision, quality of the control signal, robustness against disturbances and energy efficiency. Complementary comments are addressed based on merits and demerits of the each control technique.

Comparative performance and cost-integrated life cycle assessment of low impact development controls for sustainable stormwater management

The rapid growth of web-based applications has intensified the need for secure development methodologies. ASP.NET Core and the .NET Framework provide robust architectural models and built-in security mechanisms for developing enterprise-grade web applications. However, improper implementation can expose systems to severe vulnerabilities such as injection attacks, broken authentication, insecure deserialization, and cross-site scripting. This research explores the design principles, architectural patterns, authentication mechanisms, authorization strategies, cryptographic implementations, and secure deployment practices for ASP.NET Core and .NET Framework applications. By synthesizing existing literature (pre-2023), OWASP guidelines, and practical implementation models, this study proposes a structured security-oriented development framework. Visual models including architectural diagrams, sequence diagrams, mind maps, and comparative tables are used to enhance conceptual clarity. The research contributes a consolidated approach toward building secure, scalable, and maintainable ASP.NET-based web systems.

Experimental high-speed characterization and electrical modeling and simulation are presented for a six-layer Cu/SiO/sub 2/ on-chip wiring structure with 12.4-mm-long lines. Testing is performed over the temperature range -160/spl deg/C to +100/spl deg/C and across a 200-mm-diameter wafer. Very good agreement is reported between measured and simulated signal propagation and crosstalk waveforms. Modeling is done using a three-dimensional field solver and the R(f), L(f), and C matrices are used in a synthesized distributed network to simulate the signal behavior. Such a broadband analysis comprises the first comprehensive functional testing of a multi-layer Cu/SiO/sub 2/ wiring structure. The Cu interconnections are shown to be able to sustain 5.39 GHz microprocessor frequencies at T=+25/spl deg/C operation at a scaled wiring density increase of 17.5%, while comparable Al(Cu) wiring can achieve only 4.44 GHz (21.4% improvement).

Quadrotor UAVs are gradually being used in various fields because of their flexibility, ease of control and low cost. Along with advancement of electrical technology in contemporary times and increasing application scenarios of the aircraft, the demand for control systems has also increased. In different application scenarios, there are some differences in the functions and application requirements of UAV. Therefore, it is of great value to adjust the control algorithm by combining the scenario requirements. PID heuristic and fuzzy PID heuristic are the two most common control algorithms in UAV. In this paper, the heuristics are designed and compared for the above two algorithms in different scenarios and environments. First, the development process and status of UAVs are explained, and the importance of the control system is introduced. Subsequently, two control systems are studied and designed separately, and targeted comparison tests are conducted. Finally, the performance and applicability scenarios of the two control systems are analysed according to the experimental results, which in turn provide an important reference basis for the design of PID-based UAV control systems.

In a research and technology application project at Bellcore, we used multidatabase transactions to model multisystem work flows of telecommunication applications. During the project a prototype scheduler for executing multi-database transactions was developed. Two of the issues addressed in this project were concurrent execution of multi-database transactions and their failure recovery. This paper discusses our use of properties of the application and the telecommunication systems to develop simple and efficient solutions to the concurrency control and recovery problems.

Multi-agent networked linear dynamic systems have attracted the attention of researchers in power systems, intelligent transportation, and industrial automation. The agents might cooperatively optimize a global performance objective, resulting in social optimization, or try to satisfy their own selfish objectives using a noncooperative differential game. However, in these solutions, large volumes of data must be sent from system states to possibly distant control inputs, thus resulting in high cost of the underlying communication network. To enable economically viable communication, a game-theoretic framework is proposed under the communication cost, or sparsity, constraint, given by the number of communicating state/control input pairs. As this constraint tightens, the system transitions from dense to sparse communication, providing the tradeoff between dynamic system performance and information exchange. Moreover, using the proposed sparsity-constrained distributed social optimization and noncooperative game algorithms, we develop a method to allocate the costs of the communication infrastructure fairly and according to the agents' diverse needs for feedback and cooperation. Numerical results illustrate utilization of the proposed algorithms to enable and ensure economic fairness of wide-area control among power companies.

Powerful refrigeration methods are being deployed to cool electronic devices in test and in end-use application. Cooling capacity control is required to prevent over- or under-cooling. Various levels of control precision are also required. Test applications demand precise temperature control while many end-use applications will accommodate a less sophisticated approach. Important determinants of the method employed to control refrigeration capacity include target operating temperature, absolute and dynamic power dissipation of the device being cooled, control precision required, refrigeration system design and construction, as well as application-related details of the electronics assembly. A variety of capacity control methods are needed to cover the breadth of electronics cooling applications. Control free, or open loop systems meet the needs of some applications. Other systems employ thermal expansion (TX) and hot-gas by-pass valves to provide controlled cooling of very high power electronics cooling vapor compression systems. Modulation of condenser efficiency by varying fan speed provides a very simple but limited range of temperature control. A broad range of precise temperature control requires a combination of approaches to precisely meter refrigerant flow to the cold plate and, if needed, to apply parasitic heat. This paper overviews various vapor compression refrigeration control architectures as they apply to electronics cooling. Comparative cost and performance data are presented.

Many cost-conscious public cloud workloads (“tenants”) are turning to Amazon EC2’s spot instances because, on average, these instances offer significantly lower prices (up to 10 times lower) than on-demand and reserved instances of comparable advertised resource capacities. To use spot instances effectively, a tenant must carefully weigh the lower costs of these instances against their poorer availability. Toward this, we empirically study four features of EC2 spot instance operation that a cost-conscious tenant may find useful to model. Using extensive evaluation based on historical spot instance data, we show shortcomings in the state-of-the-art modeling of these features that we overcome. As an extension to our prior work, we conduct data analysis on a rich dataset of the latest spot price traces collected from a variety of EC2 spot markets. Our analysis reveals many novel properties of spot instance operation, some of which offer predictive value whereas others do not. Using these insights, we design predictors for our features that offer a balance between computational efficiency (allowing for online resource procurement) and cost efficacy. We explore “case studies” wherein we implement prototypes of dynamic spot instance procurement advised by our predictors for two types of workloads. Compared to the state of the art, our approach achieves (i) comparable cost but much better performance (fewer bid failures) for a latency-sensitive in-memory Memcached cache and (ii) an additional 18% cost savings with comparable (if not better than) performance for a delay-tolerant batch workload.

The radiation dose, image signal-to-noise ratio, image resolution and cost of film/screen and digital subtraction angiography have been investigated. Theoretical analysis indicates that the dose normalized signal-to-noise ratio for DSA is 50% better than film/screen methods. Iodinated vessel phantoms have confirmed this result. An evaluation of 55 patients indicates improved small vessel detection, better delineation of diffuse contrast stains, and fewer artifacts with DSA when compared with film/screen results on the same patients. Substantial reduction in cost for DSA methods is attributed to film utilization reduction as well as reduced examining times.