Workflow Tasks Research Articles

Enabling scalable and adaptive machine learning training via serverless computing on public cloud

In today’s production machine learning (ML) systems, models are continuously trained, improved, and deployed. ML design and training are becoming a continuous workflow of various tasks that have dynamic resource demands. Serverless computing is an emerging cloud paradigm that provides transparent resource management and scaling for users and has the potential to revolutionize the routine of ML design and training. However, hosting modern ML workflows on existing serverless platforms has non-trivial challenges due to their intrinsic design limitations such as stateless nature, limited communication support across function instances, and limited function execution duration. These limitations result in a lack of an overarching view and adaptation mechanism for training dynamics, and an amplification of existing problems in ML workflows.To address the above challenges, we propose SMLT, an automated, scalable and adaptive serverless framework on public cloud to enable efficient and user-centric ML design and training. SMLT employs an automated and adaptive scheduling mechanism to dynamically optimize the deployment and resource scaling for ML tasks during training. SMLT further enables user-centric ML workflow execution by supporting user-specified training deadline and budget limit. In addition, by providing an end-to-end design, SMLT solves the intrinsic problems in public cloud serverless platforms such as the communication overhead, limited function execution duration, need for repeated initialization, and also provides explicit fault tolerance for ML training. SMLT is open-sourced and compatible with all major ML frameworks. Our experimental evaluation with large, sophisticated modern ML models demonstrates that SMLT outperforms the state-of-the-art VM-based systems and existing public cloud serverless ML training frameworks in both training speed (up to 8×) and monetary cost (up to 3×).

Workflow Scheduling in Cloud–Fog Computing Environments: A Systematic Literature Review

ABSTRACTThe Internet of Things (IoT) facilitates the connectivity of billions of physical devices for exchanging information and enabling a wide range of applications. These applications can be presented in the form of dependent tasks, as outlined in a workflow. These workflows face limitations due to constraints in IoT sensors. To address these limitations, cloud computing has emerged to offer a large capacity of computing and storing with a great capability to adjust resources according to the need. However, cloud computing might not adequately meet the low‐latency of IoT workflow requirements when scheduling a workflow composed of IoT tasks due to its centralized nature. Moreover, cloud computing is not ideal for delay‐sensitive workflows and may increase communication costs. In response to these challenges, the use of fog computing as an extension to cloud computing scheme is recommended. Fog computing aims to process workflow tasks close to IoT devices. While fog computing offers various advantages, integrating these systems into workflow scheduling remains one of the most formidable challenges in distributed environments. Indeed, significant issues arise due to the timely execution and the resource limitations. In this survey paper, we present a Systematic Literature Review (SLR) on the current state of the art in this domain. We propose a taxonomy to compare and evaluate the existing studies on workflow scheduling approaches in cloud–fog computing environments. This taxonomy encompasses various criteria, including scheduling techniques, performance metrics, workflow dependencies, scheduling policies, and evaluation tools. We highlight certain recommendations for open issues which require more investigations. Our aim is to provide valuable insights for researchers and developers interested in understanding the contributions and challenges of current workflow scheduling approaches in cloud–fog computing environments.

A tri-chromosome-based evolutionary algorithm for energy-efficient workflow scheduling in clouds

Cloud computing is increasingly attracting workflow applications, where workflows need to satisfy execution deadlines and energy consumption is to be minimized. So far, numerous studies have adopted evolutionary algorithms to optimize the energy consumption of workflow execution. Dynamic voltage and frequency scaling (DVFS) has been widely employed to save energy on computing devices running workflow tasks. However, most existing evolutionary algorithms focus on evolving task execution order or mapping from tasks to resources, while neglecting the evolution of task runtime to leverage the dynamic voltage and frequency scaling (DVFS) technology for further energy saving. To compensate for that deficiency, this paper designs a tri-chromosome-based evolutionary algorithm, namely TCEA, to evolve three types of decision vectors (i.e., task order, task and resource mapping, and task runtime) simultaneously using three problem-specific mechanisms. Firstly, we construct a search space by using the tasks’ minimum and optimal runtime, and propose a solution representation mechanism to simplify the decision vector for task runtime between 0 and 1. Secondly, we design a deadline constraint handling mechanism to distribute those durations exceeding the deadline to each task based on their extension of the minimum runtime. Thirdly, we exploit the workflow structure to cluster decision variables without direct constraints into the same group. During each iteration, only the order of tasks within a group evolves to avoid precedence constraints, thus performing searches within the feasible space. At last, we conduct comparison experiments on five types of real-world workflows with 30 to 1000 tasks. The energy consumed by TCEA is much less than those consumed by the state-of-the-art workflow scheduling algorithms, demonstrating the superior performance of TCEA in energy saving.

Employing artificial intelligence to steer exascale workflows with colmena

Computational workflows are a common class of application on supercomputers, yet the loosely coupled and heterogeneous nature of workflows often fails to take full advantage of their capabilities. We created Colmena to leverage the massive parallelism of a supercomputer by using Artificial Intelligence (AI) to learn from and adapt a workflow as it executes. Colmena allows scientists to define how their application should respond to events (e.g., task completion) as a series of cooperative agents. In this paper, we describe the design of Colmena, the challenges we overcame while deploying applications on exascale systems, and the science workflows we have enhanced through interweaving AI. The scaling challenges we discuss include developing steering strategies that maximize node utilization, introducing data fabrics that reduce communication overhead of data-intensive tasks, and implementing workflow tasks that cache costly operations between invocations. These innovations coupled with a variety of application patterns accessible through our agent-based steering model have enabled science advances in chemistry, biophysics, and materials science using different types of AI. Our vision is that Colmena will spur creative solutions that harness AI across many domains of scientific computing.

RETRACTION: Workflow Task Scheduling for Homogeneous Environments on Multiprocessing Based on IoT Variant of Beta Artificial Bee Colony

RETRACTION: D. K. Shukla, J. Singh, S. Muthusamy, S. Satpathy, and V. Goyal, “,” Trans Emerg Telecommun Technol (Early View): doi:10.1002/ett.4685.The above article, published online on 1 December 2022 in Wiley Online Library (wileyonlinelibrary.com), has been retracted by agreement between the journal Editor‐in‐Chief, Changqiao Xu; and John Wiley & Sons Ltd. The article was submitted as part of a guest‐edited special issue. Following publication, it has come to the attention of the journal that the article was accepted solely on the basis of compromised editorial handling and peer review processes. Finally, multiple scientific statements in this manuscript are not sufficiently supported by references to the literature. Therefore, the decision to retract this article was taken.

From lab to field with machine learning – Bridging the gap for movement analysis in real-world environments: A commentary

Biomechanical data collection was largely confined to controlled laboratory setups, relying on marker-based systems or force platforms. However, the emergence of wearable sensors and markerless motion capture has revolutionized this field, enabling data collection in real-world scenarios. This shift has also sparked interest in integrating machine learning (ML) into biomechanical workflows, promising to revolutionize data acquisition in field settings and refine data analysis (Halilaj et al., 2018). Figure 1 provides an overview of corresponding ML applications for key tasks in the biomechanical workflow. This commentary explores the transformative potential of ML in biomechanics, focusing on enhancing data collection and analysis in real-world environments. Pose estimation (a) is the process of automatically tracking and determining the body’s anatomical landmarks, body segments, or joint centre locations in video images using ML, enabling the quantification of human movement without marker and sensor attachments to the human body. Feature estimation (b) employs ML to predict complex biomechanical data, e.g. joint moments from more accessible data sources, including IMUs, pressure insoles, and RGB video cameras. Event detection (c) in time series data is the annotation of certain events that are used to extract useful and vital information or to remove unwanted and unnecessary data for further analysis. Clustering (d) involves grouping instances or individuals with similar biomechanical characteristics using unsupervised ML, thereby revealing underlying structures and subgroups within complex biomechanical data. Finally, automated classification (e) refers to the process of developing a predictive model that assigns input features of data samples to predefined categories or classes using supervised ML. Despite the advancements of ML in biomechanics, central challenges are faced. Estimation errors remain critically high depending on the task and application field, necessitating a careful reflection on data acquisition potentials. Furthermore, especially complex Deep Learning models, while showing promising performances, exhibit a lack of transparency in understanding their decision-making processes and the underlying patterns and rules learned from the data. This phenomenon, often termed as the black-box nature of these models, poses a considerable obstacle. In response, Explainable Artificial Intelligence (XAI), a field that encompasses different explainability approaches to shed light on the inner workings of complex, non-linear ML models, has gained increasing attention in recent years (Slijepcevic et al., 2023). A further central challenge is the availability of data and annotations, which describes the limited availability or insufficiency of relevant and comprehensive datasets, as well as task-specific annotations, for conducting thorough analyses and research in biomechanics. The lack of large-scale benchmark datasets available restricts the widespread adoption of ML-based approaches in biomechanics. Privacy concerns present significant ethical and legal issues, e.g. with identifiable video data. Additionally, model validation remains a critical problem, as many studies fail to validate their models on diverse datasets, often relying on limited data from a single laboratory. Furthermore, there is a risk that the fundamental mechanical understanding of biomechanical processes might be overshadowed by an over-reliance on ML techniques. In conclusion, the integration of ML into biomechanics presents a transformative opportunity for understanding human movement by enabling and improving data collection and analysis in real-world settings. Challenges in data accessibility and methodological transparency necessitate collaborative efforts for future advancements.

Performance aware algorithm design for elastic resource workflow management of cluster consolidation to handle enterprise big data

<span lang="EN-US">Integration and deployment of big data and business analytics application with cloud computing are more attractive as a service and are trending practice. This hybrid workflow is rapidly increasing and will trigger a revolution for enterprise data handling, information retrieval and computing. This paper presents hybrid workflow management framework for big data and multi cloud computing systems in a two-step approach. Linear optimization-based resource assessment algorithm is planned in the first step. Cluster oriented elastic resource allocation and workflow management techniques are concentrated in the second step. This paper also focus on performance evaluation parameters includes execution time, through put with multi task work flow optimization model. The proposed framework is efficiently managed the implementation of hybrid workflows by finetuning the evaluation attributes and provides improvement in terms of response time an average of 6%.</span>

Workflow scheduling based on asynchronous advantage actor–critic algorithm in multi-cloud environment

Recently, the multi-cloud environment (MCE) has increasingly become the preferred choice of users. As with the cloud environment, efficient workflow scheduling in a MCE remains crucial for identifying the cost efficiency and overall performance of the MCE. In MCE, the resources exhibit heterogeneity, complexity, and dynamism. Simultaneously, the intricate inter-task dependencies among workflow tasks, diverse Quality of Service (QoS) metrics for users, and multiple cloud service providers’ (CSPs) billing mechanisms significantly amplify the workflow scheduling challenge. Motivated by the application of reinforcement learning (RL) in workflow scheduling in a cloud environment, this paper proposes a scheduling algorithm that takes advantage of the asynchronous advantage actor–critic algorithm (A3C) to balance cost, makespan and resource utilization in workflow scheduling in a MCE. By analyzing the elements in the MCE, we design and define multiple agents in the MCE, and each cloud service provider will have an agent to record the state and update the local parameters. For the workflow task submitted by the user, the action is selected according to the initialization policy and submitted to the scheduling action to allocate the task to a designated virtual machine in the MCE so that each agent can more clearly perceive the environment change and adapt to the MCE. In contrast to the traditional A3C algorithm, we design a new critic network according to the data characteristics of real-world scientific workflows so that each agent is more suitable for real-world scientific workflow data. Through multiple sets of simulation experiments, the workflow scheduling algorithm based on the A3C algorithm in the MCE (MCWS-A3C) was compared with three benchmark methods. The experimental results show that the proposed method has better advantages than other methods in terms of cost, makespan, and resource utilization. Specifically, on the Montage_100 dataset, the average cost was reduced by 55.12% compared to other methods. The pioneering introduction of the A3C algorithm that adapts to the dynamic environment into the MCE brings more possibilities to address the issue of workflow scheduling in the MCE.

Secure workflow scheduling algorithm utilizing hybrid optimization in mobile edge computing environments

The rapid advancement of mobile communication technology and devices has greatly improved our way of life. It also presents a new possibility that data sources can be used to accomplish computing tasks at nearby locations. Mobile Edge Computing (MEC) is a computing model that provides computer resources specifically designed to handle mobile tasks. Nevertheless, there are certain obstacles that must be carefully tackled, specifically regarding the security and quality of services in the workflow scheduling over MEC. This research proposes a new method called Feedback Artificial Remora Optimization (FARO)-based workflow scheduling method to address the issues of scheduling processes with improved security in MEC. In this context, the fitness functions that are taken into account include multi-objective, such as CPU utilization, memory utilization, encryption cost, and execution time. These functions are used to enhance the scheduling of workflow tasks based on security considerations. The FARO algorithm is a combination of the Feedback Artificial Tree (FAT) and the Remora Optimization Algorithm (ROA). The experimental findings have demonstrated that the developed approach surpassed current methods by a large margin in terms of CPU use, memory consumption, encryption cost, and execution time, with values of 0.012, 0.010, 0.017, and 0.036, respectively.

Optimizing scientific workflow scheduling in cloud computing: a multi-level approach using whale optimization algorithm

Cloud computing has evolved into an indispensable tool for facilitating scientific research due to its ability to efficiently distribute and process workloads in a virtual environment. Scientific tasks that involve complicated task dependencies and user-defined constraints related to quality of service (QoS) and time constraints require the efficient use of cloud resources. Planning these scientific workflow tasks represents an NP-complete problem, prompting researchers to explore various solutions, including conventional planners and evolutionary optimization algorithms. In this study, we present a novel, multistage algorithm specifically designed to schedule scientific workflows in cloud computing contexts. This approach addresses the challenges of efficiently mapping complex workflows onto distributed cloud resources while considering factors like resource heterogeneity, dynamic workloads, and stringent performance requirements. The algorithm uses the whale optimization algorithm (WOA) with a two-phase approach to shorten execution time, minimize financial costs, and effectively maintain load balancing.

Prototype pipeline modelling using interval scanning point clouds

AbstractWith the aid of computer aided design (CAD) and building information modelling (BIM), as-built to as-designed comparison has seen many developments in improving the workflow of manufacturing and construction tasks. Recently, evolution has been centred around automation of scene interpretation from three-dimensional (3D) scan data. The scope of this paper is to assess assemblies as the installation process progresses and inferring if arising deviations are problematic (complex task). The adequacy of utilising unorganised point clouds to compliance check are trialled with a real life down-scaled prototype model in conjunction with a synthetic dataset. This work aims to highlight areas where large rework could be avoided, in part by the detection of potential clashes of components early in the pipeline installation process. With the help of an extracted model in the form of a point cloud generated from a scanned physical model and a 3D CAD model representing the nominal geometry, an operator can be made visually aware of potential deviations and component clashes during a pipeline assembly process.

Multi-priority scheduling algorithm for scientific workflows in cloud

The public cloud environment has emerged as a promising platform for exe-cuting scientific workflows. These executions involve leasing virtual machines (VMs) from public services for the duration of the workflow. The structure of the workflows significantly impacts the performance of any proposed scheduling approach. A task within a workflow cannot begin its execution before receiving all the required data from its preceding tasks. In this paper, we introduce a multi-priority scheduling approach for executing workflow tasks in the cloud. The key component of the proposed approach is a mechanism that logically or-ders and groups workflow tasks based on their data dependencies and locality. Using the proposed approach, the number of available VMs influences the num-ber of groups (partitions) obtained. Based on the locality of each group’s tasks, the priority of each group is determined to reduce the overall execution delay and improve VM utilization. As the results demonstrate, the proposed approach achieves a significant reduction in both execution costs and time in most scenar-ios

CMK: Enhancing Resource Usage Monitoring across Diverse Bioinformatics Workflow Management Systems

The increasing use of multiple Workflow Management Systems (WMS) employing various workflow languages and shared workflow repositories enhances the open-source bioinformatics ecosystem. Efficient resource utilization in these systems is crucial for keeping costs low and improving processing times, especially for large-scale bioinformatics workflows running in cloud environments. Recognizing this, our study introduces a novel reference architecture, Cloud Monitoring Kit (CMK), for a multi-platform monitoring system. Our solution is designed to generate uniform, aggregated metrics from containerized workflow tasks scheduled by different WMS. Central to the proposed solution is the use of task labeling methods, which enable convenient grouping and aggregating of metrics independent of the WMS employed. This approach builds upon existing technology, providing additional benefits of modularity and capacity to seamlessly integrate with other data processing or collection systems. We have developed and released an open-source implementation of our system, which we evaluated on Amazon Web Services (AWS) using a transcriptomics data analysis workflow executed on two scientific WMS. The findings of this study indicate that CMK provides valuable insights into resource utilization. In doing so, it paves the way for more efficient management of resources in containerized scientific workflows running in public cloud environments, and it provides a foundation for optimizing task configurations, reducing costs, and enhancing scheduling decisions. Overall, our solution addresses the immediate needs of bioinformatics workflows and offers a scalable and adaptable framework for future advancements in cloud-based scientific computing.

Efficient offloading and task scheduling in internet of thingth-cloud-fog environment

Efficient offloading and scientific task scheduling are crucial for managing computational tasks in research environments. This involves determining the optimal location for executing a workflow task and allocating the task to computing resources to optimize performance. The challenge is to minimize completion time, energy consumption, and cost. This study proposes three methods: latency-centric offloading (LCO) for delay-sensitive applications; energy-based offloading (EBO) for energy-saving; and efficient offloading (EO) for balanced task distribution across tiers. Scheduling in this paper uses a genetic algorithm (GA) with a weighted sum objective function considering makespan, cost, and energy for IoT-fog-cloud. Comparative studies involving Montage, Cybershake, and epigenomics workflows indicate that LCO excels in terms of makespan and cost but ranks the lowest in energy. EBO excels in energy efficiency, aligning closely with the base method. EO competes effectively with the base method in terms of makespan and cost but consumes more energy.<strong> </strong>This research enables the selection of the most suitable method based on the type of application and its prioritization of makespan, energy, or cost.

Dynamic variable analysis guided adaptive evolutionary multi-objective scheduling for large-scale workflows in cloud computing

Energy consumption and makespan of workflow execution are two core performance indicators in operating cloud platforms. But, simultaneously optimizing these two indicators encounters various challenges, such as elastic resources, large-scale decision variables, and sophisticated workflow structures. To handle these challenges, we design an adaptive evolutionary scheduling algorithm, namely AESA, with three innovative strategies. First, a heuristic population initialization strategy is devised to gather workflow tasks onto limited potential resources, thereby alleviating the negative impact of redundant cloud resources on evolutionary search efficiency. Then, a variable analysis strategy is designed to dynamically measure the contribution of each decision variable in pushing the population towards Pareto-optimal fronts. Moreover, AESA embraces an adaptive strategy to reward more evolutionary opportunities for decision variables with higher contributions to handle large-scale decision variables in a targeted manner, further improving the efficiency of evolutionary search. Finally, extensive experiments are performed based on real-world cloud platforms and workflow traces to verify the effectiveness of the proposed AESA. The comparison results validate its superior performance by significantly outperforming five representative baselines in optimizing makespan and energy consumption. Also, the results of ablation experiments demonstrate that all three components contribute to AESA’s overall performance, with the adaptive reward mechanism being the most significant.

StreamSAXS: a Python-based workflow platform for processing streaming SAXS/WAXS data.

StreamSAXS is a Python-based small- and wide-angle X-ray scattering (SAXS/WAXS) data analysis workflow platform with graphical user interface (GUI). It aims to provide an interactive and user-friendly tool for analysis of both batch data files and real-time data streams. Users can easily create customizable workflows through the GUI to meet their specific needs. One characteristic of StreamSAXS is its plug-in framework, which enables developers to extend the built-in workflow tasks. Another feature is the support for both already acquired and real-time data sources, allowing StreamSAXS to function as an offline analysis platform or be integrated into large-scale acquisition systems for end-to-end data management. This paper presents the core design of StreamSAXS and provides user cases demonstrating its utilization for SAXS/WAXS data analysis in offline and online scenarios.

Retraction Note: An efficient cost-based algorithm for scheduling workflow tasks in cloud computing systems

Retraction Note: An efficient cost-based algorithm for scheduling workflow tasks in cloud computing systems

Advanced cost-aware Max–Min workflow tasks allocation and scheduling in cloud computing systems

Cloud computing has emerged as an efficient distribution platform in modern distributed computing offering scalability and flexibility. Task scheduling is considered as one of the main crucial aspects of cloud computing. The primary purpose of the task scheduling mechanism is to reduce the cost and makespan and determine which virtual machine (VM) needs to be selected to execute the task. It is widely acknowledged as a nondeterministic polynomial-time complete problem, necessitating the development of an efficient solution. This paper presents an innovative approach to task scheduling and allocation within cloud computing systems. Our focus lies on improving both the efficiency and cost-effectiveness of task execution, with a specific emphasis on optimizing makespan and resource utilization. This is achieved through the introduction of an Advanced Max–Min Algorithm, which builds upon traditional methodologies to significantly enhance performance metrics such as makespan, waiting time, and resource utilization. The selection of the Max–Min algorithm is rooted in its ability to strike a balance between task execution time and resource utilization, making it a suitable candidate for addressing the challenges of cloud task scheduling. Furthermore, a key contribution of this work is the integration of a cost-aware algorithm into the scheduling framework. This algorithm enables the effective management of task execution costs, ensuring alignment with user requirements while operating within the constraints of cloud service providers. The proposed method adjusts task allocation based on cost considerations dynamically. Additionally, the presented approach enhances the overall economic efficiency of cloud computing deployments. The findings demonstrate that the proposed Advanced Max–Min Algorithm outperforms the traditional Max–Min, Min–Min, and SJF algorithms with respect to makespan, waiting time, and resource utilization.

IMG-32. USER EVALUATION OF AN AI-POWERED WEB APPLICATION TO SUPPORT RADIOGRAPHIC INTERPRETATION OF PATIENTS WITH ADAMANTINOMATOUS CRANIOPHARYNGIOMA

Abstract BACKGROUND In neuro-oncology, accurately interpreting radiographic images, especially for diagnosing central nervous system (CNS) tumors like Adamantinomatous Craniopharyngioma (ACP), presents formidable challenges. Even with advanced imaging technologies such as Magnetic Resonance Imaging (MRI) and Computed Tomography (CT), pinpointing features related to ACP invasiveness remains daunting. METHODS We introduced an interactive web application that utilizes a custom AI model to analyze preoperative MRI and CT images of 50 patients with ACP. This application can predict a 12-point radiographic feature profile and rank patients based on similarity, aiming to support clinicians in making more precise diagnoses. We deployed our application on a hospital-grade radiographic reading terminal. Our application’s utility and user-friendliness were evaluated through a user study involving four neurosurgeons and two neuroradiologists, who constructed 12-point radiographic feature profiles for ten patients within a 30-minute timeframe given patient MRI and CT images. RESULTS Our study subjects reported high self-assessed numeracy (SNS scores ranging from 4 to 5.25) despite varied preferences in engaging with numerical data. Subjects could efficiently learn to navigate our software interface, with an average task completion time of approximately 3 minutes and 25 seconds per patient. Introducing AI into the task workflow resulted in a slight, statistically non-significant increase in completion time, indicating that while AI modifies interaction dynamics, it does not significantly hinder efficiency in task performance. We observed distinct agreement patterns between clinicians and AI prediction, utilizing Fleiss’ Kappa for categorization. AI assistance subtly boosted clinicians’ confidence and slightly lessened the perceived difficulty of interpreting radiographic images. However, these benefits were not statistically significant. CONCLUSIONS Our study highlights the promise of AI in improving neuro-oncology diagnostics, showing that clinicians quickly adapted to an AI-enhanced application, which subtly influenced their radiographic interpretation. This finding underscores the potential for AI to enhance decision-making accuracy in challenging cases like ACP.

Synergizing human expertise and AI efficiency with language model for microscopy operation and automated experiment design * *Notice: This manuscript has been authored by UT-Battelle, LLC, under Contract No. DE-AC0500OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a non-exclusive, paid-up,

With the advent of large language models (LLMs), in both the open source and proprietary domains, attention is turning to how to exploit such artificial intelligence (AI) systems in assisting complex scientific tasks, such as material synthesis, characterization, analysis and discovery. Here, we explore the utility of LLMs, particularly ChatGPT4, in combination with application program interfaces (APIs) in tasks of experimental design, programming workflows, and data analysis in scanning probe microscopy, using both in-house developed APIs and APIs given by a commercial vendor for instrument control. We find that the LLM can be especially useful in converting ideations of experimental workflows to executable code on microscope APIs. Beyond code generation, we find that the GPT4 is capable of analyzing microscopy images in a generic sense. At the same time, we find that GPT4 suffers from an inability to extend beyond basic analyses for more in-depth technical experimental design. We argue that an LLM specifically fine-tuned for individual scientific domains can potentially be a better language interface for converting scientific ideations from human experts to executable workflows. Such a synergy between human expertise and LLM efficiency in experimentation can open new doors for accelerating scientific research, enabling effective experimental protocols sharing in the scientific community.