New cloud services are being developed to support a wide variety of real-life applications. In this paper, we introduce a new cloud service: industrial automation, which includes different functionalities from feedback control and telemetry to plant optimization and enterprise management. We focus our study on the feedback control layer as the most time-critical and demanding functionality. Today's large-scale industrial automation projects are expensive and time-consuming. Hence, we propose a new cloud-based automation architecture, and we analyze cost and time savings under the proposed architecture. We show that significant cost and time savings can be achieved, mainly due to the virtualization of controllers and the reduction of hardware cost and associated labor. However, the major difficulties in providing cloud-based industrial automation systems are timeliness and reliability. Offering automation functionalities from the cloud over the Internet puts the controlled processes at risk due to varying communication delays and potential failure of virtual machines and/or links. Thus, we design an adaptive delay compensator and a distributed fault tolerance algorithm to mitigate delays and failures, respectively. We theoretically analyze the performance of the proposed architecture when compared to the traditional systems and prove zero or negligible change in performance. To experimentally evaluate our approach, we implement our controllers on commercial clouds and use them to control: (i) a physical model of a solar power plant, where we show that the fault-tolerance algorithm effectively makes the system unaware of faults, and (ii) industry-standard emulation with large injected delays and disturbances, where we show that the proposed cloud-based controllers perform indistinguishably from the best-known counterparts: local controllers.

Cloud computing requires further research and development to accommodate more application areas [5]. We introduce a new application area: industrial automation. A current industrial automation (IA) system is a multi-tiered architecture entailing different layers from feedback control to enterprise management. If adopted in large-scale IA systems, cloud computing can offer over 40% cost saving and 25--85% time saving [4, 1]. However, IA requires tighter timeliness, reliability, and security than most other cloud applications. We propose a cloud-based IA architecture and focus on the timeliness and reliability requirements. Addressing such requirements for the lowest layer (feedback control) is the most challenging. We addressed the timeliness problem in [2]. To address reliability and further address timeliness, we propose a distributed fault tolerance algorithm for cloud-based controllers. We theoretically and practically prove that the proposed fault-tolerant, cloud-based controllers offer the same performance of the local ones.

This paper presents two proactive resource allocation algorithms, called RBA* and OBA, for asynchronous real-time distributed systems. The algorithms consider an application model where timeliness requirements are expressed using Jensen's benefit functions and propose adaptation functions to describe anticipated application workload during future time intervals. Furthermore, the algorithms consider an adaptation model, where application processes are dynamically replicated for sharing workload increases and a switched real-time Ethernet network as the underlying system model. Given such models, the objective of the algorithms is to maximize the aggregate application benefit and minimize the aggregate missed deadline ratio. Since determining the optimal allocation is computationally intractable, the algorithms heuristically compute near-optimal resource allocations in polynomial-time. While RBA* analyzes the process response times to determine resource allocation decisions, which is computationally expensive, OBA analyzes processor overloads to compute its decisions in a much faster way. RBA* incurs a quadratic amortized complexity in terms of process arrivals for its most computationally intensive component when DASA is used as the underlying scheduling algorithm, whereas OBA incurs a logarithmic amortized complexity for the corresponding component. Our benchmark-driven experimental studies reveal that RBA* produces a higher aggregate benefit and lower missed deadline ratio than OBA.

We present a "predictive" resource management algorithm for periodic tasks in real-time distributed applications that are characterized by significant execution-time uncertainties. The algorithm is predictive in the sense that it forecasts the timeliness behavior of the tasks during the resource allocation process and select allocations that yield the optimal forecasted timeliness. The algorithm uses statistical regression theory for predicting task timeliness. The performance of the predictive algorithm is studied by comparing with a nonpredictive resource management algorithm that uses heuristic rules for allocating resources. The experimental results indicate that the predictive algorithm outperforms the non-predictive algorithm when the workload shows fluctuating behavior.

Presents feedback control techniques for performing adaptive resource management in asynchronous real-time distributed systems. Such systems are characterized by significant execution time uncertainties in the application environment and system resource state. Thus, such systems require adaptive resource management that dynamically monitor the system for adherence to the desired real-time requirements and perform run-time adaptation of the application to changing workloads when unacceptable timeliness behavior is observed. We propose adaptive resource management techniques that are based on feedback control theory. The controllers solve resource allocation problems that arise during run-time adaptation using the classical proportional-integral-derivative (PID) control functions. We study the performance of the controllers through simulation. The simulation results indicate that the controllers produce low missed deadline ratios and resource utilizations during situations of high workloads.

This paper describes an implementation and the performance evaluation of the DASAATD best-effort scheduling algorithm [4] in the pC1id/pCsinunm micro-controller system Experimental results under synthetic wrkload show that in some cases, the DASALND scheduler outperfom both the EDF (Earliest Deadline First) and the RMS (Rate Monotonic Scheduling) schedulers [7]. Meanwhile, the system performance gracefully degrades as the aggregate CPU Load increases. However, the scheduling overhead in general, is not negligible, which may lead to poorer performance than non best-effort scheduling algorithms. It is found that the schealuling overhead strongly depends on the task set properties. Using the Regression Analysis technique, we developed a statistical model accounting for the scheduling overhead We show that this model, combined with a simulation tool can well predict the system performance.

Presents intelligent feedback control techniques for adaptive resource management in asynchronous, decentralized real-time systems. We propose adaptive resource management techniques that are based on feedback control theory and are designed using the intelligent control design paradigm. The controllers solve resource allocation problems that arise during run-time adaptation using the classic proportional-integral-derivative (PID) control functions and fuzzy logic. We study the performance of the controllers through simulation. The simulation results indicate that the controllers produce low missed deadline ratios and resource utilizations during high-workload situations.