Toward a Self-Adaptive Workflow Management System Through Learning and Prediction Models

Samiri, Mohamed Yassine; Najib, Mehdi; Fazziki, Abdelaziz El; Boukachour, Jaouad

doi:10.1007/s13369-016-2372-3

Cited by 6 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth noting that ARIMA has been proposed to tackle some specific situations, such as ARIMAX, SARMA, FAR-MAX, which are used respectively to process exogenous variables, manage the seasonality in time-series data and integrate fuzzy logic. ARIMA's accuracy relies mainly on the selection of the model through the identification of the parameters p, i and q, where p is the lags count for the AR model, i is an integration order, which is needed to make the data stationary, and q is the lags count for the MA model [45]. However, as the three methods, LSTM, CNN, and ARIMA, are tested in this study, the training process is done either in the in-vehicle embedded device or in an external infrastructure (e.g., a distant server).…”

Section: Cnn Is a Class Of Artificial Neural Network (Ann) It Is Used...mentioning

confidence: 99%

Embedded Real-Time Speed Forecasting for Electric Vehicles: A Case Study on RSK Urban Roads

et al. 2022

View full text Add to dashboard Cite

During the past ten years, worldwide efforts have been pursuing an ambitious policy of sustainable development, particularly in the energy sector. This ambition was revealed by noticeable progress in the deployment and development of infrastructures for the production of renewable electrical energy. These infrastructures combined with the deployment of wired and wireless communications could support research actions in the field of connected electro-mobility. Also, this progress was manifested by the development of electric vehicles (EV), penetrating our transportation roads more and more. They are considered among the potential solutions, which are envisaged to further reduce road transport's greenhouse gas emissions, relying on low-carbon energy production. However, the uncertainty caused by both external road disturbances and drivers' behavior could influence the prediction of upcoming power demands. These latter are mainly affected by the unpredictability of the electric vehicles' speed on transportation roads. In this work, we introduce an energy management platform, which interfaces with in-vehicle components, using a developed embedded system, and external services, using IoT and big data technologies, for efficient battery power use. The platform was deployed in real-setting scenarios and tested for EV speed prediction. In fact, we have used driving data, which have been collected on Rabat-Salé-Kénitra (RSK) urban roads by our Twizy EV. A multivariate Long Short Term Memory (LSTM) algorithm was developed and deployed for speed forecasting. The effectiveness of LSTM was evaluated against well-known algorithms: Auto Regressive Integrated Moving Average (ARIMA), Convolutional Neural Network (CNN) and Convolutional LSTM (ConvLSTM). Experiments have been conducted using two approaches; the whole trajectory dataset and segmented trajectory datasets to train the models. The experimentation results show that LSTM outperforms the other used algorithms in terms of forecasting the speed, especially when using the trajectory segmentation approach.INDEX TERMS Electro-mobility, Intelligent Transportation Systems, Speed forecasting, Time-series forecasting, Deep learning I. INTRODUCTIONN OWADAYS, electric vehicles (EVs) are penetrating more and more transportation roads. There are three main categories of EVs: Hybrid Electric Vehicles (HEV), Plugin Hybrid Electric Vehicles (PHEV), and Batterypowered Electric Vehicles (BEV). BEVs are fully-electric vehicles with rechargeable batteries. HEV and PHEV are, however, powered by both gasoline and electricity. Unlike PHEV, which can be recharged through both regenerative braking and external electricity sources, HEV is charged from the electricity generated by the car's braking system. However, both of them are still using gasoline, which is one of the sources of greenhouse gas.BEVs have been getting more attention in the last years, as they are environment-friendly while having an acceptable driving range, particularly in urban areas. BEV driving range

show abstract

Section: Cnn Is a Class Of Artificial Neural Network (Ann) It Is Used...mentioning

confidence: 99%

Embedded Real-Time Speed Forecasting for Electric Vehicles: A Case Study on RSK Urban Roads

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Regarding adaptive capabilities, it is also possible to find many approaches related to regular workflows (Siebert, 1999;Chung et al, 2003;Narendra, 2004;Müller et al, 2004;Ardissono et al, 2006;Dang et al, 2008;Samiri et al, 2017). However, as explained in Sections 1 and 2, LRWs have not their execution and adaptation managed in a similar way to regular ones.…”

Section: Related Workmentioning

confidence: 99%

An execution environment as a service for adaptive long-running workflows

Souza-Júnior

Rosa

Lins

2021

IJWIS

View full text Add to dashboard Cite

Purpose This paper aims to present Long4Cloud (long-running workflows execution environment for cloud), a distributed and adaptive LRW execution environment delivered “as a service” solution. Design/methodology/approach LRWs last for hours, days or even months and their duration open the possibility of changes in business rules, service interruptions or even alterations of formal regulations of the business before the workflow completion. These events can lead to problems such as loss of intermediary results or exhaustion of computational resources used to manage the workflow execution. Existing solutions face those problems by merely allowing the replacement (at runtime) of services associated with activities of the LRW. Findings LONG4Cloud extends the previous works in two main aspects, namely, the inclusion of dynamic reconfiguration capabilities and the adoption of an “as a service” delivery mode. The reconfiguration mechanism uses quiescence principles, data and state management and provides multiple adaptive strategies. Long4Cloud also adopts a scenario-based analysis to decide the adaptation to be performed. Events such as changes in business rules or service failures trigger reconfigurations supported by the environment. These features have been put together in a solution delivered “as a service” that takes advantage of cloud elasticity and allows to better allocate cloud resources to fit into the demands of LRWs. Originality/value The original contribution of Long4Cloud is to incorporate adaptive capabilities into the LRW execution environment as an effective way to handle the specificities of this kind of workflow. Experiments using current data of a Brazilian health insurance company were carried out to evaluate Long4Cloud and show performance gains in the execution of LRWs submitted to the proposed environment.

show abstract

“…• From the modeling side, the formalization of a D&D System as a system of systems including the properties described by (Maier, 1998); • From the management side and especially during project piloting, the implementation of a process management based on the principle of adaptive workflow as proposed for instance by (Samiri et al, 2017). These two concepts are used and needed throughout the life cycle of the D&D system.…”

Section: Progressmentioning

confidence: 99%

A Model‐Based Approach to Design, Organize, and Monitor Dismantling and Decommissioning of Nuclear Facilities

Lafon¹,

Chapurlat²,

Milot³

et al. 2019

INSIGHT

View full text Add to dashboard Cite

Dismantling and Decommissioning (D&D) of nuclear facilities involves complex operations requiring the collaboration of a large number of stakeholders from various activities, and has to deal with numerous significant constraints. The CEA (French Alternative Energies and Atomic Energy Commission), is conducting research to better pilot these operations and reduce their costs and timeframes, and to improve overall performance. To this end, many issues remain to be solved, which lead to studying, then implementing in the form of a method with appropriate tools, the principles from systemics and the engineering of complex projects and systems. This method first consists in formalizing and specifying the entire set of requirements to be taken into consideration. Second, based on these requirements, the method will enable the project team to structure, check, and then to demonstrate the coherence and feasibility of the project from both the technological and organizational points of view. Lastly, the method should permit a constant re-evaluation of the D&D strategy and the management of its products, depending on the possible evolution of the D&D projects. Demonstration software is being developed, aiming to provide the functionalities requested for the design, implementation and maintenance of a future enterprise software, which should provide a complete D&D project Digital Mock-Up being interoperable and connected to the tools and databases of the stakeholders' information systems.

show abstract

Toward a Self-Adaptive Workflow Management System Through Learning and Prediction Models

Cited by 6 publications

References 25 publications

Embedded Real-Time Speed Forecasting for Electric Vehicles: A Case Study on RSK Urban Roads

Embedded Real-Time Speed Forecasting for Electric Vehicles: A Case Study on RSK Urban Roads

An execution environment as a service for adaptive long-running workflows

A Model‐Based Approach to Design, Organize, and Monitor Dismantling and Decommissioning of Nuclear Facilities

Contact Info

Product

Resources

About