Runtime Operation Research Articles

Multi-stage framework for optimal incorporating of inverter based distributed generator into distribution networks

Recently, hydrogen-based distributed generators (DG) have gained significant attention for modern energy generation systems. These modem DGs are typically outfitted with power electronics converters, resulting in harmonic pollution. Furthermore, increasing the growth of modern nonlinear loads may result in exceeding the harmonic beyond the permitted level. This research proposes a framework for optimal incorporation of inverter-based distributed generation (a fuel cell connected to an AC distribution system) for minimizing power losses, enhancing the voltage profile, and limiting both total and individual harmonic distortion according to the IEEE-519 standard. In addition, for accounting system sustainability, the proposed framework considers load variation and the expected rise in demand. Therefore, the suggested framework comprises three stages, which include fundamental and harmonic power flow analysis. The first stage identifies the optimal size and location of the DG in relation to the base load operating condition. While, with the optimal DG of the first stage, the amount of harmonic pollution may violate the limits during a high level of nonlinear load penetration, as a result, the second stage resizes the DG, considering the connection bus of the first stage, to mitigate the harmonics and optimize the system at a higher level of nonlinear load penetration. Both the first and second stages are performed off-line, while the third stage optimizes the system operation during run time according to loading conditions, harmonic pollution, and the available DG capacity of the previous stages. DG’s harmonic spectrum is represented according to recently issued IEEE 1547-2018 for permissible DG’s current distortion limits. The suggested approach is applied and evaluated using an IEEE 33-bus distribution system for various combinations of linear and nonlinear loads. For run-time operation throughout the day, the presented framework reduces the energy losses from 5.281 to 2.452 MWh/day (about 53.57% energy savings). This saving is associated with voltage profile enhancement without violating the permissible standard levels of harmonics and other system constraints.

NetOr: A Microservice Oriented Inter-Domain Vertical Service Orchestrator for 5G Networks

Most modern 5G Vertical Service Orchestrators present various limitations. Among these, one may high-light (i) the employment of monolithic architectures, (ii) the lack of standardized APIs and methodologies, (iii) the minimum support for inter-domain scenarios, and (iv) the impossibility of performing run-time operations over Vertical Services. To achieve a fully-fledged Vertical Service Orchestrator, these problems must be solved. This is the focus of the work presented in this article. Our work presents a new 5G Vertical Service orchestration system named NetOr, which tackles all the listed limitations and can support complex and intricate use cases. NetOr was implemented according to a microservice architecture. Thus, it has increased flexibility, scalability, and maintainability. Moreover, NetOr inherited most advantages of the modern Vertical Service Orchestrators and, therefore, can be considered an improvement of said orchestrators. Furthermore, this work also presents a Proof-of-Concept solution to achieve inter-domain communication through the orchestration of an End-To-End Network Slice that establishes several VPN tunnels between the domains encompassed by the Network Slice.

RescueSNN: enabling reliable executions on spiking neural network accelerators under permanent faults.

To maximize the performance and energy efficiency of Spiking Neural Network (SNN) processing on resource-constrained embedded systems, specialized hardware accelerators/chips are employed. However, these SNN chips may suffer from permanent faults which can affect the functionality of weight memory and neuron behavior, thereby causing potentially significant accuracy degradation and system malfunctioning. Such permanent faults may come from manufacturing defects during the fabrication process, and/or from device/transistor damages (e.g., due to wear out) during the run-time operation. However, the impact of permanent faults in SNN chips and the respective mitigation techniques have not been thoroughly investigated yet. Toward this, we propose RescueSNN, a novel methodology to mitigate permanent faults in the compute engine of SNN chips without requiring additional retraining, thereby significantly cutting down the design time and retraining costs, while maintaining the throughput and quality. The key ideas of our RescueSNN methodology are (1) analyzing the characteristics of SNN under permanent faults; (2) leveraging this analysis to improve the SNN fault-tolerance through effective fault-aware mapping (FAM); and (3) devising lightweight hardware enhancements to support FAM. Our FAM technique leverages the fault map of SNN compute engine for (i) minimizing weight corruption when mapping weight bits on the faulty memory cells, and (ii) selectively employing faulty neurons that do not cause significant accuracy degradation to maintain accuracy and throughput, while considering the SNN operations and processing dataflow. The experimental results show that our RescueSNN improves accuracy by up to 80% while maintaining the throughput reduction below 25% in high fault rate (e.g., 0.5 of the potential fault locations), as compared to running SNNs on the faulty chip without mitigation. In this manner, the embedded systems that employ RescueSNN-enhanced chips can efficiently ensure reliable executions against permanent faults during their operational lifetime.

Design and Validation of a Low-Level Controller for Hierarchically Controlled Exoskeletons.

In this work, a generalized low-level controller is presented for sensor collection, motor input, and networking with a high-level controller. In hierarchically controlled exoskeletal systems, which utilize series elastic actuators (SEAs), the hardware for sensor collection and motor command is separated from the computationally expensive high-level controller algorithm. The low-level controller is a hardware device that must collect sensor feedback, condition and filter the measurements, send actuator inputs, and network with the high-level controller at a real-time rate. This research outlines the hardware of two printed circuit board (PCB) designs for collecting and conditioning sensor feedback from two SEA subsystems and an inertial measurement unit (IMU). The SEAs have a joint and motor encoder, motor current, and force sensor feedback that can be measured using the proposed generalized low-level controller presented in this work. In addition, the high and low-level networking approach is discussed in detail, with a full breakdown of the data storage within a communication frame during the run-time operation. The challenges of device synchronization and updates rates of high and low-level controllers are also discussed. Further, the low-level controller was validated using a pendulum test bed, complete with full sensor feedback, including IMU results for two open-loop scenarios. Moreover, this work can be extended to other hierarchically controlled robotic systems that utilize SEA subsystems, such as humanoid robots, assistive rehabilitation robots, training simulators, and robotic-assisted surgical devices. The hardware and software designs presented in this work are available open source to enable researchers with a direct solution for data acquisition and the control of low-level devices in a robotic system.

In-depth study of RNTI management in mobile networks: Allocation strategies and implications on data trace analysis

The advance of mobile network technologies and components heavily relies on data-driven techniques. This is especially true for fifth generation (5G) and the upcoming sixth generation (6G) networks, as the optimization of network components and protocols is expected to be fueled by artificial intelligence (AI) based solutions. When using real-world radio access measurement traces, the identity of individual users is not directly accessible because at runtime operation Base Stations (BSs) assign Radio Network Temporary Identifiers (RNTIs) to users. RNTIs are not bound to a user but are reused upon expiration of an inactivity timer, whose duration is operator dependent. This implies that, over time, multiple users are mapped to the same RNTI. In fact, the allocation of RNTIs to users is implemented in diverse and proprietary ways by operators and equipment vendors. Distinguishing individual users within the RNTI space is a non-trivial task and key to analyze traffic traces properly. In this paper, we make the following contributions: (i) we propose and validate two complementary methodologies to identify the RNTI inactivity threshold, and we characterize (ii) the RNTI allocation process of network operators, and (iii) the user traffic patterns given the specific RNTI allocation process. Our study is based on a large dataset we collected from production BSs of several mobile network operators across five different countries. We find that there exist heterogeneous strategies for RNTI allocation that BSs dynamically use depending on the traffic load and daytime. We further observe that the RNTI expiration threshold is in the order of minutes, and demonstrate how using thresholds around 10 s, as in the vast majority of the literature, can bias subsequent analyses. Overall, our work provides an important step towards dependable mobile network trace analysis, and lays solid foundations to research relying on traffic traces for data-driven analysis.

A new real-time lossless data compression algorithm for ECG and PPG signals

ObjectiveData compression is a useful process in tele-monitoring applications, in which lesser number of bits are needed to represent the same data. In this work, a run-time lossless compression of single-channel Electrocardiogram (ECG) and Photoplethysmogram (PPG) signals is proposed, maintaining all dominant features. MethodsThe single-channel data are first quantized using optimal quantization level, so that fewer number of bits are needed to represent it, maintaining low quantization error. Then, second order delta encoding and run-length encoding (RLE) based data compression are proposed in this work. A new approach of using ‘buffer array’ along with RLE is also introduced, so that minimum bits are needed to store. ResultsThis algorithm was tested on various single-lead ECG and PPG signals available in Physionet. An average compression ratio (CR) was achieved of 6.52, 3.82, and 2.49 for 547 PTBDB ECG records, 48 MITDB ECG records, and 53 MIMIC-II PPG records, respectively. This algorithm was also performed on single-channel ECG, collected from 10 healthy volunteers using AD8232 ECG module, with 125 Hz sampling frequency and 10-bit data resolution, which resulted in average CR of 2.34. ConclusionThis algorithm was also performed on a smartphone device that provided user-friendly operation. The low computational complications and standalone operation of data collection, compression, and transmission encouraged its implementation for run-time operation. SignificanceA comparative study of the proposed work with previously published works proved this fact that this algorithm provided better performance in the area of run-time patient health monitoring applications.

Runtime Monitoring of Time Window Temporal Logic

Temporal logic is becoming increasingly popular for its application in the analysis and control of dynamic systems. Time window temporal logic (TWTL) is a rich expressive language for specifying time-bounded serial tasks in a compact manner that is common in many control applications, such as robotics. Typically, TWTL specifications are verified using an automata-based model checking algorithm. However, verification of important properties of a given system using model checking in design time does not guarantee that the system will behave as expected during the runtime operation which falls under the scope of runtime verification. In this letter, we present a rewriting-based algorithm for runtime monitoring of safety requirements expressed in TWTL. The feasibility and efficiency of our proposed approach is demonstrated using two case studies related to unmanned aerial vehicle (UAV) surveillance and industrial robotics for manufacturing.

Reliable Deep Learning and IoT-Based Monitoring System for Secure Computer Numerical Control Machines Against Cyber-Attacks With Experimental Verification

This paper introduces a new intelligent integration between an IoT platform and deep learning neural network (DNN) algorithm for the online monitoring of computer numerical control (CNC) machines. The proposed infrastructure is utilized for monitoring the cutting process while maintaining the cutting stability of CNC machines in order to ensure effective cutting processes that can help to increase the quality of products. For this purpose, a force sensor is installed in the milling CNC machine center to measure the vibration conditions. Accordingly, an IoT architecture is designed to connect the sensor node and the cloud server to capture the real-time machine’s status via message queue telemetry transport (MQTT) protocol. To classify the different cutting conditions (i.e., stable cutting and unstable cuttings), an improved model of DNN is designed in order to maintain the healthy state of the CNC machine. As a result, the developed deep learning can accurately investigate if the transmitted data of the smart sensor via the internet is real cutting data or fake data caused by cyber-attacks or the inefficient reading of the sensor due to the environment temperature, humidity, and noise signals. The outstanding results are obtained from the proposed approach indicating that deep learning can outperform other traditional machine learning methods for vibration control. The Contact elements for IoT are utilized to display the cutting information on a graphical dashboard and monitor the cutting process in real-time. Experimental verifications are performed to conduct different cutting conditions of slot milling while implementing the proposed deep machine learning and IoT-based monitoring system. Diverse scenarios are presented to verify the effectiveness of the developed system, where it can disconnect immediately to secure the system automatically when detecting the cyber-attack and switch to the backup broker to continue the runtime operation.

A Novel Multiagent Resource Sharing Algorithm for Control of Advanced Energy Systems

This paper implements a novel resource sharing control strategy on a fuel cell–gas turbine hybrid power system at the National Energy Technology Laboratory’s Hybrid Performance Facility (Hyper). In a fuel cell–gas turbine hybrid power system, the simultaneous interaction of the gas turbine and the fuel cell creates a tightly coupled environment characterized by conflicting dynamics. In this paper, a model-free control approach is applied to solve the tightly coupled control problem posed by this challenging environment. Specifically, this control problem is presented as a resource sharing problem that can be solved using a resource sharing algorithm that is defined based on the distribution construction concept. This algorithm creates computational agents and solves the problem through the distribution and redistribution of shared resources defined as blocks. Two agents were created; the first agent (agent 1) controls the gas turbine speed by adjusting the electric load, and the second agent (agent 2) controls the cathode mass flow through the fuel cell using the cold-air bypass valve. A parametric study was performed over the course of 15 experimental tests for both agents 1 and 2 through an evaluation of the responses based on setpoint changes. The algorithm was shown to have behavior comparable to a previously implemented multi-input multioutput state-space controller, which was designed through a model-based control approach. The resource sharing algorithm was able to find stable performance during run-time operations without any prior system knowledge identification on the power plant and without creating models used in traditional control strategies.

Hybrid Verification Technique for Decision-Making of Self-Driving Vehicles

The evolution of driving technology has recently progressed from active safety features and ADAS systems to fully sensor-guided autonomous driving. Bringing such a vehicle to market requires not only simulation and testing but formal verification to account for all possible traffic scenarios. A new verification approach, which combines the use of two well-known model checkers: model checker for multi-agent systems (MCMAS) and probabilistic model checker (PRISM), is presented for this purpose. The overall structure of our autonomous vehicle (AV) system consists of: (1) A perception system of sensors that feeds data into (2) a rational agent (RA) based on a belief–desire–intention (BDI) architecture, which uses a model of the environment and is connected to the RA for verification of decision-making, and (3) a feedback control systems for following a self-planned path. MCMAS is used to check the consistency and stability of the BDI agent logic during design-time. PRISM is used to provide the RA with the probability of success while it decides to take action during run-time operation. This allows the RA to select movements of the highest probability of success from several generated alternatives. This framework has been tested on a new AV software platform built using the robot operating system (ROS) and virtual reality (VR) Gazebo Simulator. It also includes a parking lot scenario to test the feasibility of this approach in a realistic environment. A practical implementation of the AV system was also carried out on the experimental testbed.

Data Membership Identification using Bloom Filter in Cloud Storage for Effective Resource Allocation

Cloud computing has recently been the buzz word that had changed the entire software industry with its PaaS, IaaS and SaaS architecture model. The legacy systems operational in the organizations across different industries have been using the database that had an overhead in terms of cost of data storage, runtime operation and frequent data maintenance. Cloud database concept had challenged the existing storage and operational norms of data. In the distributed environment, resources used in the cloud databases need to identify whether the requested data belongs to the data nodes of a cluster. With databases began to be ubiquitous, the data storage needed to satisfy heterogeneous data structures rather the unstructured data storage support is looked for. The Use of Bloom's filter for data membership identification is the novel approach and can effectively improve the resource organization strategy on cloud. Dynamic resource organization can further improve the query efficiency as well. The concern raised during this is the data privacy which can also be ascertain by maintaining the data access authority levels. Bloom filter uses less memory space against the large dataset to store it's information. A Bloom filter is proposed to be used to determine whether an element is part of a reference set. It is a very compact hash-based data structure with efficient look-up times and a manageable risk of giving false positives.

Orchestrated Scheduling and Multi-Agent Deep Reinforcement Learning for Cloud-Assisted Multi-UAV Charging Systems

This paper proposes a cloud-assisted joint charging scheduling and energy management framework for unmanned aerial vehicle (UAV) networks. For charging the UAVs those are extremely power hungry, charging towers are considered for plug-and-play charging during run-time operations. The charging towers should be cost-effective, thus it is equipped with photovoltaic power generation and energy storage systems functionalities. Furthermore, the towers should be cooperative for more cost-effectiveness by intelligent energy sharing. Based on the needs and setting, this paper proposes 1) charging scheduling between UAVs and towers and 2) cooperative energy managements among towers. For charging scheduling, the UAVs and towers should be scheduled for maximizing charging energy amounts and the scheduled pairs should determine charging energy allocation amounts. Here, two decisions are correlated, i.e., it is a non-convex problem. We re-formulate the non-convex to convex for guaranteeing optimal solutions. Lastly, the cooperative energy sharing among towers is designed and implemented with multi-agent deep reinforcement learning and then intelligent energy sharing can be realized. We can observe that the two methods are related and it should be managed, coordinated, and harmonized by a centralized orchestration manager under the consideration of fairness, energy-efficiency, and cost-effectiveness. Our data-intensive performance evaluation verifies that our proposed framework achieves desired performance.

Fuzzy classification of OpenCL programs targeting heterogeneous systems

Heterogeneous systems featuring multiple kinds of processors are becoming increasingly attractive due to their high performance and energy savings over their homogeneous counterparts. With the OpenCL as a unified programming language providing program portability across different types of accelerators, finding the best task-to-device mapping will be the key to achieve such a high performance. We introduce in this work the design of a fuzzy logic classifier and the evaluation of its performance in classifying OpenCL workloads in a CPU-GPU-FPGA heterogeneous environment based on carefully analyzed kernel features. The classifier is designed as part of a scheduling scheme. Results demonstrate substantial improvement in accuracy when compared to other classifiers such as the K-Nearest- Neighbor (KNN), Support-Vector-Machine (SVM), Random-Forest (RF), Naïve-Bayes (NB) and the Bayes-Network (BN) with low computational complexity, facilitating run-time operation.

RESEARCH AND DESIGN OF INSPECTION CLOUD PLATFORM FRAMEWORK FOR SURVEYING AND MAPPING PRODUCTS

Abstract. With the continuous improvement of modern surveying and mapping technology and with the plentiful of achievements, traditional quality inspection software for single machine, single task and single data type, difficult to massive multi-source isomerization achievements, difficult to meet the requirement of rapid, accurate and efficient quality inspection. With the development of IT technology such as cloud computing, big data and artificial intelligence, the quality inspection software needs to combine cloud computing technology with quality inspection business, refactoring software framework. Facing to the storage and spatial query requirement of inspection for surveying and mapping products, the paper researches and designs the spatial data distributed storage and the spatial data distributed index in cloud platform. The Management of inspection rule is the core in cloud platform. Inspection rule is the minimum operating independent unit, which becomes inspection item by parameterization, the paper builds full run-time operating mechanism in cloud platform for inspection rule. Finally, Combining the inspection requirement for surveying and mapping products and business, the paper researches and design the cloud framework for surveying and mapping products.

Model-Based Monitoring and Adaptation of Pacemaker Behavior Using Hierarchical Fuzzy Colored Petri-Nets

A pacemaker is an embedded device that is sited in the chest to regulate irregular heartbeats known as arrhythmias. Since such devices are directed by software, a software failure may cause a serious hazard such as patient death. Runtime monitoring and adaptation of the device software behavior offers a solution for preventing device hazards. We have already obtained some experiences from monitoring medical devices like: 1) insulin pump using fuzzy Petri net and 2) cardiac pacemaker using colored Petri-net (CPN) and hierarchical fuzzy CPN (HFCPN). However, these studies did not present an adaptation method for software runtime faults. This paper, extending our previous work, presents an automatic runtime method for continuous verification of the behavior of the implanted pacemaker using a software agent. The autonomy and the intelligence characteristics of the software agent are used to control the behavior of the cardiac pacemaker software by drawing inferences from a knowledge base where HFCPN is used by the agent as the inference engine. Compared to a flat inference engine, the HFCPN is able to cover the concurrent states initiated by input fuzzy values and improve the running time for finding a suitable rule by up to 92%. In addition, the intelligent software agent checks the runtime operation accuracy of the pacemaker software in vital and unexpected situations, and redirects the software decision if it finds an unacceptable value. To demonstrate the HFCPN’s behavior and decision-making in different situations, three different scenarios are presented.

Cross-point Resistive Memory

Emerging computational resistive memory is promising to overcome the challenges of scalability and energy efficiency that DRAM faces and also break through the memory wall bottleneck. However, cell-level and array-level nonideal properties of resistive memory significantly degrade the reliability, performance, accuracy, and energy efficiency during memory access and analog computation. Cell-level nonidealities include nonlinearity, asymmetry, and variability. Array-level nonidealities include interconnect resistance, parasitic capacitance, and sneak current. This review summarizes practical solutions that can mitigate the impact of nonideal device and circuit properties of resistive memory. First, we introduce several typical resistive memory devices with focus on their switching modes and characteristics. Second, we review resistive memory cells and memory array structures, including 1T1R, 1R, 1S1R, 1TnR, and CMOL. We also overview three-dimensional (3D) cross-point arrays and their structural properties. Third, we analyze the impact of nonideal device and circuit properties during memory access and analog arithmetic operations with focus on dot-product and matrix-vector multiplication. Fourth, we discuss the methods that can mitigate these nonideal properties by static parameter and dynamic runtime co-optimization from the viewpoint of device and circuit interaction. Here, dynamic runtime operation schemes include line connection, voltage bias, logical-to-physical mapping, read reference setting, and switching mode reconfiguration. Then, we highlight challenges on multilevel cell cross-point arrays and 3D cross-point arrays during these operations. Finally, we investigate design considerations of memory array peripheral circuits. We also portray an unified reconfigurable computational memory architecture.

A Framework for Optimization, Service Placement, and Runtime Operation in the Fog

A Framework for Optimization, Service Placement, and Runtime Operation in the Fog

SeArch: A Collaborative and Intelligent NIDS Architecture for SDN-Based Cloud IoT Networks

The explosive rise of intelligent devices with ubiquitous connectivity have dramatically increased Internet of Things (IoT) traffic in the cloud environment and created potential attack surfaces for cyber-attacks. Traditional security approaches are insufficient and inefficient to address security threats in cloud-based IoT networks. In this vein, software defined networking (SDN), network function virtualization (NFV), and machine learning techniques introduce numerous advantages that can effectively resolve cybersecurity matters for cloud-based IoT systems. In this paper, we propose a collaborative and intelligent network-based intrusion detection system (NIDS) architecture, namely SeArch for SDN-based cloud IoT networks. It composes a hierarchical layer of intelligent IDS nodes working in collaboration to detect anomalies and formulate policy into the SDN-based IoT gateway devices to stop malicious traffic as fast as possible. We first describe a new NIDS architecture with a comprehensive analysis in terms of the system resource and path selection optimizations. Next, the system process logic is extensively investigated through main consecutive procedures, including initialization, runtime operation, and database update. Afterward, we conduct a detailed implementation of the proposed solution in an SDN-based environment and perform a variety of experiments. Finally, evaluation results of the SeArch architecture yield outstanding performance in anomaly detection and mitigation as well as bottleneck problem handling in the SDN-based cloud IoT networks in comparison with existing solutions.

A Review of the Principles of Designing Smart Cyber-Physical Systems for Run-Time Adaptation: Learned Lessons and Open Issues

Smart cyber-physical systems (S-CPSs) are complex engineered systems empowered by cyber-physical computing and equipped with the capability of reasoning, learning, adapting, and evolving. As an outcome of data-driven dynamic computing, reasoning capabilities, and the run-time obtained own knowledge, nonlinear and emergent behavior of S-CPSs whilst in operation is an open issue, not experienced in the case of conventional technical systems. This paper analyzes the technical issues of run-time operation and emergent behavior of S-CPSs, reviews the current understanding and state of advancement in designing S-CPSs for run-time, explores the paradox, and issues of designing for run-time adaptation, and synthesizes some general principles that can be taken into consideration when addressing the challenges, first of all, in the context of advanced manufacturing systems. This paper introduces four levels of CPSs according to reasoning capabilities and adaptation freedom of systems, and recognizes the paradox that a system with a higher level of freedom requires a higher level of self-control and resource management according to the overall objective of operation. Specific and common design principles are presented and critically assessed for each advancement level of CPSs. The principles synthesized by the authors provide only a partial fulfillment of the generic need. The planned future research addresses these issues and proposes (largely implementation and application independent) genuine principles for system developers.

Use of On-Demand Cloud Services to Model the Optimization of an Austenitization Furnace

Abstract This article describes a smart manufacturing framework, comprising an on-demand, cloud-based deployment of a modeling application in a manufacturing operation. A specific use case, the optimization of the austenitization of steel parts, is presented. The framework uses a Kepler workflow as a cloud service to orchestrate and manage the data and computations required to implement a run-time model-based control and optimization approach on Amazon Web Services (AWS) resources. Austenitization is an energy intensive heat treating process commonly employed to harden and strengthen ferrous metals, such as steel. Pre-finished steel parts are heated to a specific temperature in a continuously operating industrial austenitization furnace without oxidizing the surface. The steel parts are then rapidly cooled or quenched in an oil bath. There is significant potential to optimize energy productivity by managing the energy usage needed to achieve the properties of the metal part instead of managing to operational process settings. Models of this process, which predict the furnace energy consumption and temperatures of parts as a function of time and position in the furnace and map temperatures to properties, have been previously developed; however, for operational use, the data and models need to be orchestrated for run-time operation, access to infrastructure, scalability, security, and support. A cloud-based approach is an alternative to the on-premise approach, in which an infrastructure for data, computational, and security needs to be built and maintained to support the application. A workflow service makes it possible to combine and sequence simulation and optimization software applications developed in several distinct MATLAB (The Mathworks Inc., Natick, MA) model configurations that are needed for various data-based calculations. The final output of the computation is the optimal operating condition of the furnace that minimizes the fuel consumption without violating the part target specifications. The workflow can be triggered on demand by an operator of the furnace or run at periodic intervals. All the computational resources required are instantiated and run at the start of the workflow and shutdown at the end of the workflow.