Submitted Successfully!
To reward your contribution, here is a gift for you: A free trial for our video production service.
Thank you for your contribution! You can also upload a video entry or images related to this topic.
Version Summary Created by Modification Content Size Created at Operation
1 -- 2808 2022-09-12 09:32:40 |
2 update references and layout Meta information modification 2808 2022-09-13 05:45:35 |

Video Upload Options

Do you have a full video?


Are you sure to Delete?
If you have any further questions, please contact Encyclopedia Editorial Office.
Feeken, L.;  Kern, E.;  Szanto, A.;  Winnicki, A.;  Kao, C.;  Wudka, B.;  Glawe, M.;  Mirzaei, E.;  Borchers, P.;  Burghardt, C. Anomalies in a Factory of the Future. Encyclopedia. Available online: (accessed on 21 April 2024).
Feeken L,  Kern E,  Szanto A,  Winnicki A,  Kao C,  Wudka B, et al. Anomalies in a Factory of the Future. Encyclopedia. Available at: Accessed April 21, 2024.
Feeken, Linda, Esther Kern, Alexander Szanto, Alexander Winnicki, Ching-Yu Kao, Björn Wudka, Matthias Glawe, Elham Mirzaei, Philipp Borchers, Christian Burghardt. "Anomalies in a Factory of the Future" Encyclopedia, (accessed April 21, 2024).
Feeken, L.,  Kern, E.,  Szanto, A.,  Winnicki, A.,  Kao, C.,  Wudka, B.,  Glawe, M.,  Mirzaei, E.,  Borchers, P., & Burghardt, C. (2022, September 12). Anomalies in a Factory of the Future. In Encyclopedia.
Feeken, Linda, et al. "Anomalies in a Factory of the Future." Encyclopedia. Web. 12 September, 2022.
Anomalies in a Factory of the Future

Production systems are changing in many aspects on the way to a Factory of the Future, including the level of automation and communication between components. Besides all benefits, this evolution raises the amount, effect and type of anomalies and unforeseen behavior to a new level of complexity.

manufacturing Factory of the Future resilience

1. Introduction

The increasing level of digital networking of the factory landscape and the rising level of automation of its components and other key elements of Industry 4.0 technology offers high potential for increasing productivity, flexibility and sustainability and enables new business models in the Factory of the Future (FoF) [1]. At the same time, increasing connectivity and automation are creating new vulnerabilities in the FoF environment [2], e.g., by cyber-attacks targeting the emerging interfaces [3] and malfunctioning/secured automated systems. In this dynamic environment, resilient manufacturing systems need to be designed and enabled to recover from an undesired state (e.g., as a result of a cyber operation penetrating the infrastructure) and return to a desired state [4]. Hence, increasing the resilience of the FoF is of high importance for the manufacturing sector. To increase the resilience in the networked FoF environment, systems must be able to detect situations where they are in such an undesired state and initiate appropriate actions to return to a desired state. This leads to the requirement to develop methods to detect anomalies, reduce their frequency (avoiding undesired states) and mitigate the effects of anomalies (regaining desired states). One of the challenges in detecting anomalies in the FoF environment is dealing with the increased flexibility: since the FoF environment is designed to operate very dynamically and is confronted with changing tasks, it is not feasible to derive standard system models whose properties can be compared with monitoring data to identify anomalies [5]. When dealing with cyber threats, existing legacy IoT systems pose a particular challenge as these systems were not originally designed for use in highly connected environments and are thus poorly secured [6][7]. The necessity and importance to mitigate cyber threats is widely emphasized: “Research and industry efforts should provide short-term solutions to mitigate the impact of vulnerabilities. For example, detection and correction of anomalies must be explored, rather than focusing on access control techniques only. As for automotive systems […], prevention measures may interfere with the production chain and induce downtime: thus, a delicate balance between detection and prevention should be considered” [7]. Not only are security concerns motivating ongoing research, there is also a need for methods to increase resilience to “conventional” anomalies as stated in [8]: “Nevertheless, methods for intrinsic resilience with regard to internal disruptions, such as machine failure or unscheduled downtime, are still lacking”. Furthermore, the survey in [9] underlines the need for integrated safety and security concepts in industrial control systems.

2. Attack Vectors

Cybercrime is a booming business. The sector is becoming increasingly professionalized. This is also proven by the increased number of Cybercrime-as-a-Service (CCaaS) organizations. It has never been easier to run cyber-attacks, even for persons without much technical knowledge. The relevant services can be acquired in the darknet. This can range from (customized) ransomware, encryption and extortion software and the usage of botnets to Distributed-Denial-of-Service (DDoS) attacks. Clients can often also buy personal data for subsequent social engineering attacks. In this case, information about the targeted persons is exploited to make a message look as authentic as possible. The most frequent acquired CCaaS is the development and distribution of malware software of any kind [10]. Essentially, any service that companies can purchase from legitimate managed service providers can also be purchased by CCaaS groups, just for illegal activities.
Ransomware, also known as Ransomware-as-a-Service (RaaS), is probably the most popular subtype of CCaaS. However, even beyond as-a-service offerings, ransomware is booming. Ransomware is a type of malware that encrypts files in the targeted environment. The victims are then asked to pay a ransom for the decryption of the files. There is often now a risk of double extortion, meaning that the attackers not only encrypt the files, but before doing so, they transfer the files to an offsite location. Thereby, they can threaten to publish or leak data if the ransom is not paid [11].
SonicWall states in its 2022 cyber-threat report a volume of 623.3 million ransomware attacks in 2021. This is an increase of 105% from 2020 and 231% compared to 2019 [12]. In its 2021 data breach report, IBM reports average costs of 4.62 million USD. This amount does not include the ransom payments, but includes “only” costs for incident response, notification and loss of business [13].
Phishing is a widely used method to gain access to secured networks. The X-Force Threat Intelligence Index 2022 by IBM Security stated that in 41% of the observed infections with, for example, malware by the X-Force Incident Response in 2021, phishing was the method used to gain initial access [14]. Currently, phishing is the number one method for gaining access, taking over from the exploitation of vulnerabilities [12]. Phishing aims at sending deceptively real communication via email or text message. Most often, the goal is access to passwords or other credentials. Spear-phishing is a targeted phishing campaign against one organization.
A networked FoF means that previously isolated OT environments have more IT-connections within a factory, but also to the outside world. This is a possible vulnerability, in particular in the case of Cyber Supply Chain Attacks (CSCA). Supply chain attacks can be described as the exploitation of “third-party services and software to compromise a final target” [15].
One has to make a distinction between two types of CSCA: targeted attacks and collateral damage. In the case of targeted attacks, the connections of a third-party with access to a targeted network are deliberately used. These can be for example external suppliers of a type of software. Lower security measures between trusted parties are specifically exploited to infiltrate the environment of the final target. In the case of collateral damage attacks, the infrastructure of supply chains is exploited to spread malware and increase the attack surface [16].
Even in 2019, 60% of the surveyed organizations of a study conducted by Gartner stated that they worked together with more than 1000 suppliers. Furthermore, 71% declared that their number of suppliers had increased over the last three years [17]. It can be assumed that this number has increased further over the last years. This creates various interfaces and dependencies between organizations that can be exploited and already have been, as the compromise of the SolarWinds software in 2020 showed, as well as the cyber-attack on Kaseya in 2021.

3. Threat Actors

Cyber-criminals attempt to penetrate networks by exploiting any accessible vulnerability. In doing so, they primarily pursue two main goals: on the one hand, they want to gain assets (money or valuable data), and on the other hand, they seek to avoid legal consequences by disguising themselves and their activities. A significant part of the financial damage is not even direct, in particular not in industrial networks. Many scams result primarily in indirect costs that can also affect suppliers and other dependent clients, end users and customers and may not become evident until years later. Some of these costs are difficult to measure, as they represent intangible assets such as reputation, customer trust, intellectual property (IP), brand name, insurance premiums and several others. These hidden costs can quickly add up and cause significant damage that is far greater than the measurable direct impact of the actual event [18]. The most common activities of cyber-criminals can be divided into three categories:
  • Mass fraud and automated hacking: Use of automated tools (with as little human effort as possible) to monetize large-scale fraud.
  • Providers of criminal infrastructures: These actors try to infect as many systems as possible in order to exploit them in a criminal infrastructure (e.g., botnets). They may also sell/rent the exploitation of this infrastructure to third parties.
  • Skilled professionals: Expend significant effort to attack individual high-value targets. This type of attack may use specially designed malware with a significant effort, or the attacks are carried out across supply chain partners. High-value targets in an organization are also targeted by email and phone scams, using social engineering skills to extend the attack [19].
Cyber-criminals pose the greatest threat to FoF. However, the range of cyber-crime is very wide, and the potential threats must therefore be considered on an individual basis.
State actors pursue a variety of goals, such as gathering information or supporting national interests (e.g., obtaining financial assets, stealing technological know-how or monitoring dissidents). They employ economic espionage to improve the capabilities of domestic companies. However, strategic sabotage is also a means that nation-state actors use to damage the economy or sabotage military infrastructure. In doing so, they do not make a strict distinction between civilian and military infrastructure. Infrastructures (botnets) are also created to conceal their own identity.
This cyber-operational capability can be established in two ways, which can also be combined. On the one hand, well-positioned intelligence services (financial resources and large numbers of experienced personnel) can carry out such strategic operations. On the other hand, criminal structures and organizations that are not directly attributable to the state can be used for this purpose. Those state-sponsored groups are usually easier to identify but can be more easily denied by the state [20]. These activities by state actors may well pose a threat to companies if they represent a strategic target, e.g., if the company is a world market leader in certain domain or produces unique products/components.
Disgruntled employees who are alienated for various reasons such as salary demands, promotion, appreciation, resignation, etc. and want to harm their company can pose an insider threat. Moreover, employees who are bribed and prove less loyal to their employer as the financial incentives are too lucrative can also pose a major threat. Blackmail can also occur and result in the company being harmed. While disgruntled insiders try to harm their own company in different ways by retaliation, mercenary insiders are paid well for their services.
Preventing insider activity is challenging because individuals need access to trade secrets and systems to perform their duties. However, restrictions on access should thus be automatic with the leaving of the company, as access after dismissal can be used for retaliation. Moreover, depending on the positions they hold, former employees may be well versed in the infrastructure and can circumvent restrictions if necessary. The possible transfer of sensitive data before leaving the company should also be considered, depending on the area of work. Insiders are usually tracked by efficient logging and monitoring systems after their successful activities. Insiders can be abused by other threat actors (e.g., cyber-criminals), but in this case, they are considered threat vectors rather than threat actors.
Industrial espionage by competitors has always been a proven means of gaining access to trade secrets and blueprints in order to save and circumvent the often considerable investments that many companies make in the development of intellectual property. There are countless cases of industrial espionage by competitors that run in the grey area of legality and often beyond.
By the mid-2000s, Deloitte employed a whole team of accountants, veterans and intelligence officers to run undercover operations to gather as much information as possible about competitors and explore how to win prospective clients with insights about their rivals [21]. This unit may have played an important role in 2009, when Deloitte acquired a division from another large consulting firm that held many lucrative federal contracts that was in financial trouble at the time [22].
This example shows that economic competitors have long been a potential threat to companies, and not just since the technical possibilities enabled by the internet for spying and hiding. Nevertheless, cyber-operations open up entirely different possibilities for business intelligence and other active operations to capture trade secrets and other intelligence vital to the competitors. Marketing campaign information for products or the timing of product launches could be exploited to either gain an advantage by better targeting the market or to harm the competitor. Competitors can thereby follow two main approaches: either they rely on competitive intelligence, sometimes also referred to as business or corporate intelligence, which in the original sense means the collection and analysis of all publicly available information about, for example, customers and suppliers of competitors [23], or they rely on corporate sabotage and try, for example, to damage the reputation of an important competitor in various ways (cyber-attacks on IT and OT, data theft, damage to reputation through false claims in public). While competitive intelligence is in a grey area in some areas, corporate sabotage is already illegal. Such threats should not be underestimated by organizations, as competitors may be willing to run offensive operations in the digital fog due to the attribution problem. With good chances of success and a low risk of detection, some competitors may be willing to take a chance. Companies should not lightly ignore these threat actors.

4. Anomaly Detection and Mitigation

Anomalies refer to data in a data set that differ from the expected data [24]. An anomaly can either be a a small set of data points or even a single data point that differs significantly from the normally recorded data (point anomalies, e.g., the battery level of an automated guided vehicle (AGV) equals zero, which should never happen), a data instance that is only abnormal in a specific context (contextual anomalies, e.g., a peak in the number of transport tasks at a time in which normally only a low number of tasks is expected) or a set of related data instances, which only in combination differ from expected data (collective anomalies, e.g., quickly repeated messages of an AGV on joining and then again leaving a fleet of AGVs, each message on its own is not abnormal, only the sequence of messages is deviating from the expected data) [25]. Anomaly detection is the problem of identifying anomalies, such that the detected anomalies can be mitigated afterwards. Anomalies such as unplanned production downtimes cost industrial manufacturers around $50 billion per year [26]. Hence, it is not surprising that the timely detection of anomalies is already the focus of a large number of research activities [25][27][28][29]. As already stated in the Introduction, the high dynamics and the high level of connectivity between production systems offer new potential for optimized production but lead at the same time to new challenges in anomaly detection, such as the problem of detecting anomalies in frequently changing factory situations and the detection of cyber-attacks in addition to anomalies in system and process behavior. Recent research trends tackling at least aspects of those challenges include the usage of Digital Twins (DT) for anomaly detection [30][31]. Additionally, artificial intelligence methods are developed to conduct anomaly classification tasks in manufacturing contexts, e.g., in the detection of anomalies in acoustics, such as deviations in the movement of robot arms [32], detection of anomalies in networks and communication [33] and the analysis of time series data [34]. Big Data analysis methods are also applied for anomaly detection [35], e.g., in [36] for quality control and in [37] for energy management. Although there are many methods available for the detection of specific anomalies, there are only few methodologies that address a wide range of anomalies, leading to holistic anomaly detection methods [38][39][40].
Big factory setups have various kinds of failures that can happen over a day. To withstand failures, new systems have to be robust on the one hand and resilient on the other [41]. Therefore, to increase the resilient behavior of systems and decrease the impact of failures, Gu [8] declared that redundancy and flexibility are major attributes to be built in. For this purpose, mitigation processes are widely used. In general, mitigation means to reduce or dissolve any effects of harm to a system and its environment. The mitigation of a system a can be performed by reconfiguring or adapting systems in response to a system or environmental change. However, reconfiguration is most likely used for system setups with a possible long duration of system downtime and a great diversity of system stages [8]. System stages can be described as the possibility to change system strategies (drive fast, equal wear and tear, etc.) or the replacement of systems by redundant systems. Currently, reconfiguration is split into two major ideas. (1) Global reconfiguration: A set of systems are connected and thus are represented as a fleet. Reconfiguration in this context is changing the behavior for all systems in the fleet to tackle factory goals as a group [42][43][44][45]. (2) Local reconfiguration: Each individual system can change its behavior to tackle individual system goals [46][47][48]. Even if the approaches differ, the reconfiguration process is performed in the same manner. The literature in general has concentrated on MAPE-K [49], where each letter represents one step to overcome system failure by e.g., reconfiguration. MAPE stands for monitoring, analyze, plan and execution; finally, K for knowledge represents data storage, which is used to set and compare monitored data, identify failures by analysis, determine a suitable preventive strategy by planning and implement a new strategy into the fleet or system setup.


  1. Mohamed, M. Challenges and benefits of industry 4.0: An overview. Int. J. Supply Oper. Manag. 2018, 5, 256–265.
  2. Vaidya, S.; Ambad, P.; Bhosle, S. Industry 4.0–A Glimpse. Procedia Manuf. 2018, 20, 233–238.
  3. Ahanger, T.A.; Aljumah, A. Internet of Things: A comprehensive study of security issues and defense mechanisms. IEEE Access 2018, 7, 11020–11028.
  4. Sheffi, Y. Resilience: What it is and how to achieve it. Retrieved Oct. 2008, 1, 2013.
  5. Choi, S.; Youm, S.; Kang, Y.S. Development of scalable on-line anomaly detection system for autonomous and adaptive manufacturing processes. Appl. Sci. 2019, 9, 4502.
  6. Wu, Y.; Dai, H.N.; Tang, H. Graph neural networks for anomaly detection in industrial internet of things. IEEE Internet Things J. 2021, 9, 9214–9231.
  7. Quarta, D.; Pogliani, M.; Polino, M.; Maggi, F.; Zanchettin, A.M.; Zanero, S. An Experimental Security Analysis of an Industrial Robot Controller. In Proceedings of the 2017 IEEE Symposium on Security and Privacy (SP), San Jose, CA, USA, 22–24 May 2017; pp. 268–286.
  8. Gu, X.; Jin, X.; Ni, J.; Koren, Y. Manufacturing system design for resilience. Procedia Cirp 2015, 36, 135–140.
  9. Kriaa, S.; Cambacedes, L.P.; Bouissou, M.; Halgand, Y. A survey of approaches combining safety and security for industrial control systems. Reliab. Eng. Syst. Saf. 2015, 139, 156–178.
  10. Laufenburg, R. Cybercrime-as-a-Service. 2021. Available online: (accessed on 19 May 2022).
  11. Panda Security. 73 Ransomware Statistics Vital for Security in 2022. 2022. Available online: (accessed on 31 May 2022).
  12. SonicWall. 2022 SonicWall Cyber Threat Report. 2022. Available online: (accessed on 28 July 2022).
  13. IBM Security. Cost of a Data Breach Report 2021. 2021. Available online: (accessed on 28 July 2022).
  14. IBM Security. X-Force Threat Intelligence Index 2022. 2022. Available online: (accessed on 28 July 2022).
  15. Symantec. Internet Security Threat Report. 2019, Volume 24. Available online: (accessed on 28 July 2022).
  16. Kern, E.; Szanto, A. Cyber Supply Chain Attacks. Brandenburgisches Institut für Gesellschaft und Sicherheit. BIGS Policy Paper 10, forthcoming.
  17. Bryan, J. A Better Way to Manage Third-Party Risk. 2019. Available online: (accessed on 31 May 2022).
  18. Smith, Z.M.; Lostri, E.; Lewi, J.A. The Hidden Costs of Cybercrime. McAfee, 2020. Available online: (accessed on 28 July 2022).
  19. Fortinet. Global Threat Landscape Report. A Semiannual Report by FortiGuard Labs. 1H 2021. 2021. Available online: (accessed on 28 July 2022).
  20. FireEye Mandiant Services. M-Trends 2020 Special Report. 2020. Available online: h (accessed on 28 July 2022).
  21. Dunn, P. Deloitte and the Ethics of Corporate Espionage. In Proceedings of the International Association for Business and Society, Hong Kong SAR, China, 6–10 June 2018; Number 29. pp. 65–70.
  22. Javers, E. Accountants and Spies: The Secret History of Deloitte’s Espionage Practice. 2016. Available online: (accessed on 31 May 2022).
  23. Porter, M.E. Competitive Strategy: Techniques for Analyzing Industries and Competitors; University of Michigan Free Press: Ann Arbor, MI, USA, 1980.
  24. Davis, N.; Raina, G.; Jagannathan, K. A framework for end-to-end deep learning-based anomaly detection in transportation networks. Transp. Res. Interdiscip. Perspect. 2020, 5, 100112.
  25. Chandola, V.; Banerjee, A.; Kumar, V. Anomaly detection: A survey. ACM Comput. Surv. CSUR 2009, 41, 1–58.
  26. IndustryWeek in collaboration with Emerson How Manufacturers Can Achieve Top Quartile Performance. 2016. Available online: (accessed on 19 July 2022).
  27. Kamat, P.; Sugandhi, R. Anomaly detection for predictive maintenance in industry 4.0-A survey. In E3S Web of Conferences; EDP Sciences: Les Ulis, France, 2020; Volume 170, p. 02007.
  28. Sharma, B.; Sharma, L.; Lal, C. Anomaly detection techniques using deep learning in IoT: A survey. In Proceedings of the 2019 International Conference on Computational Intelligence and Knowledge Economy (ICCIKE), Dubai, United Arab Emirates, 11–12 December 2019; pp. 146–149.
  29. Landauer, M.; Onder, S.; Skopik, F.; Wurzenberger, M. Deep Learning for Anomaly Detection in Log Data: A Survey. arXiv 2022, arXiv:2207.03820.
  30. Trauer, J.; Pfingstl, S.; Finsterer, M.; Zimmermann, M. Improving Production Efficiency with a Digital Twin Based on Anomaly Detection. Sustainability 2021, 13, 10155.
  31. Bécue, A.; Maia, E.; Feeken, L.; Borchers, P.; Praça, I. A New Concept of Digital Twin Supporting Optimization and Resilience of Factories of the Future. Appl. Sci. 2020, 10, 4482.
  32. Duman, T.B.; Bayram, B.; İnce, G. Acoustic Anomaly Detection Using Convolutional Autoencoders in Industrial Processes. In Proceedings of the 14th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2019); Martínez Álvarez, F., Troncoso Lora, A., Sáez Muñoz, J.A., Quintián, H., Corchado, E., Eds.; Springer International Publishing: Cham, Switzerland, 2020; pp. 432–442.
  33. Münz, G.; Li, S.; Carle, G. Traffic Anomaly Detection Using K-Means Clustering. In GI/ITG Workshop MMBnet; University of Bamberg Press: Bamberg, Germany, 2007; Volume 7, p. 9.
  34. Hsieh, R.J.; Chou, J.; Ho, C.H. Unsupervised online anomaly detection on multivariate sensing time series data for smart manufacturing. In Proceedings of the 2019 IEEE 12th Conference on Service-Oriented Computing and Applications (SOCA), Kaohsiung, Taiwan, 18–21 November 2019; pp. 90–97.
  35. Windmann, S.; Maier, A.; Niggemann, O.; Frey, C.; Bernardi, A.; Gu, Y.; Pfrommer, H.; Steckel, T.; Krüger, M.; Kraus, R. Big data analysis of manufacturing processes. J. Phys. Conf. Ser. 2015, 659, 012055.
  36. Stojanovic, L.; Dinic, M.; Stojanovic, N.; Stojadinovic, A. Big-data-driven anomaly detection in industry (4.0): An approach and a case study. In Proceedings of the 2016 IEEE International Conference on Big Data (Big Data), Washington, DC, USA, 5–8 December 2016; pp. 1647–1652.
  37. Zhang, C.; Wang, Z.; Ding, K.; Chan, F.T.; Ji, W. An energy-aware cyber physical system for energy Big data analysis and recessive production anomalies detection in discrete manufacturing workshops. Int. J. Prod. Res. 2020, 58, 7059–7077.
  38. Hollerer, S.; Kastner, W.; Sauter, T. Towards a threat modeling approach addressing security and safety in OT environments. In Proceedings of the 2021 17th IEEE International Conference on Factory Communication Systems (WFCS), Linz, Austria, 9–11 June 2021; pp. 37–40.
  39. Novak, T.; Treytl, A.; Palensky, P. Common approach to functional safety and system security in building automation and control systems. In Proceedings of the 2007 IEEE Conference on Emerging Technologies and Factory Automation (EFTA 2007), Patras, Greece, 25–28 September 2007; pp. 1141–1148.
  40. Antón, S.D.; Schotten, H.D. Putting together the pieces: A concept for holistic industrial intrusion detection. In Proceedings of the ECCWS 2019 18th European Conference on Cyber Warfare and Security, Coimbra, Portugal, 4–5 July 2019; Academic Conferences and Publishing Limited: Reading, UK, 2019; p. 178.
  41. Bauer, D.; Böhm, M.; Bauernhansl, T.; Sauer, A. Increased resilience for manufacturing systems in supply networks through data-based turbulence mitigation. Prod. Eng. Res. Dev. 2021, 15, 385–395.
  42. Hu, M.; Liao, Y.; Wang, W.; Li, G.; Cheng, B.; Chen, F. Decision Tree-Based Maneuver Prediction for Driver Rear-End Risk-Avoidance Behaviors in Cut-In Scenarios. J. Adv. Transp. 2017, 2017, 7170358.
  43. Xia, W.; Goh, J.; Cortes, C.A.; Lu, Y.; Xu, X. Decentralized coordination of autonomous AGVs for flexible factory automation in the context of Industry 4.0. In Proceedings of the 2020 IEEE 16th International Conference on Automation Science and Engineering (CASE), Hong Kong, China, 20–21 August 2020; pp. 488–493.
  44. Herrero-Perez, D.; Matinez-Barbera, H. Decentralized coordination of autonomous agvs in flexible manufacturing systems. In Proceedings of the 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, Nice, France, 22–26 September 2008; pp. 3674–3679.
  45. Yao, F.; Keller, A.; Ahmad, M.; Ahmad, B.; Harrison, R.; Colombo, A.W. Optimizing the scheduling of autonomous guided vehicle in a manufacturing process. In Proceedings of the 2018 IEEE 16th International Conference on Industrial Informatics (INDIN), Porto, Portugal, 18–20 July 2018; pp. 264–269.
  46. Salehie, M.; Tahvildari, L. Towards a Goal-Driven Approach to Action Selection in Self-Adaptive Software. Softw. Pract. Exp. 2012, 42, 211–233.
  47. Rosa, L.; Rodrigues, L.; Lopes, A.; Hiltunen, M.; Schlichting, R. Self-Management of Adaptable Component-Based Applications. IEEE Trans. Softw. Eng. 2013, 39, 403–421.
  48. Mauro, J.; Nieke, M.; Seidl, C.; Yu, I.C. Context Aware Reconfiguration in Software Product Lines. In Proceedings of the Tenth International Workshop on Variability Modelling of Software-Intensive Systems, VaMoS ’16, Salvador, Brazil, 27–29 January 2016; pp. 41–48.
  49. Sinreich, D. An architectural blueprint for autonomic computing. In Technical Report; IBM: New York, NY, USA, 2006.
Contributors MDPI registered users' name will be linked to their SciProfiles pages. To register with us, please refer to : , , , , , , , , ,
View Times: 333
Revisions: 2 times (View History)
Update Date: 13 Sep 2022