Applying deep learning to reduce large adaptation spaces of self-adaptive systems with multiple types of goals

Donckt, Jeroen Van Der; Weyns, Danny; Quin, Federico; Donckt, Jonas Van Der; Michiels, Sam

doi:10.1145/3387939.3391605

Cited by 33 publications

(30 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3 https://github.com/smartarch/trust4.0-demo 4 https://www.tensorflow.org/ (version 2.4) 5 We have been experimenting with Dropout layers as well, but they were causing significant underfitting in our case. Figure 2 compares the accuracy of tested configurations after 100 epochs.…”

Section: A Methodology and Datasetsmentioning

confidence: 99%

“…Namely, the approaches are as follows. In [5], neural networks are applied during the analysis and planning phase to reduce large adaptation space when the system has multiple adaptation goals and possible optimization strategies. In our approach, we apply neural networks during the same phases but our goal is to relax strict conditions and thus allow for more flexible adaptation.…”

Section: Related Workmentioning

confidence: 99%

“…In typical cases, the neural network is used for the analysis and planning stages of the MAPE-K loop and it replaces the more traditional means of analyzing the situation and deciding on actions, which are often in some form of logical rules (e.g., if-then rules or some form of a state machine with guards and actions) [2], [4], [5].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Towards fuzzification of adaptation rules in self-adaptive architectures

Bureš¹,

Hnětynka²,

Kruliš³

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper, we focus on exploiting neural networks for the analysis and planning stage in selfadaptive architectures. The studied motivating cases in the paper involve existing (legacy) self-adaptive architectures and their adaptation logic, which has been specified by logical rules. We further assume that there is a need to endow these systems with the ability to learn based on examples of inputs and expected outputs. One simple option to address such a need is to replace the reasoning based on logical rules with a neural network. However, this step brings several problems that often create at least a temporary regress. The reason is the logical rules typically represent a large and tested body of domain knowledge, which may be lost if the logical rules are replaced by a neural network. Further, the black-box nature of generic neural networks obfuscates how the systems work inside and consequently introduces more uncertainty. In this paper, we present a method that makes it possible to endow an existing self-adaptive architectures with the ability to learn using neural networks, while preserving domain knowledge existing in the logical rules. We introduce a continuum between the existing rule-based system and a system based on a generic neural network. We show how to navigate in this continuum and create a neural network architecture that naturally embeds the original logical rules and how to gradually scale the learning potential of the network, thus controlling the uncertainty inherent to all soft computing models. We showcase and evaluate the approach on representative excerpts from two larger real-life use cases.

show abstract

Section: A Methodology and Datasetsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Towards fuzzification of adaptation rules in self-adaptive architectures

Bureš¹,

Hnětynka²,

Kruliš³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…A different line of work uses supervised machine learning to reduce the size of the adaptation space. As an example, Van Der Donckt et al use deep learning to determine a representative and much smaller subset of the adaptation space [41]. However, supervised learning requires labeled training data representative of the system's environment, which may be challenging to obtain due to design time uncertainty.…”

Section: Considering Large Adaptation Spaces and Evolutionmentioning

confidence: 99%

Realizing self-adaptive systems via online reinforcement learning and feature-model-guided exploration

et al. 2022

View full text Add to dashboard Cite

A self-adaptive system can automatically maintain its quality requirements in the presence of dynamic environment changes. Developing a self-adaptive system may be difficult due to design time uncertainty; e.g., anticipating all potential environment changes at design time is in most cases infeasible. To realize self-adaptive systems in the presence of design time uncertainty, online machine learning, i.e., machine learning at runtime, is increasingly used. In particular, online reinforcement learning is proposed, which learns suitable adaptation actions through interactions with the environment at runtime. To learn about its environment, online reinforcement learning has to select actions that were not selected before, which is known as exploration. How exploration happens impacts the performance of the learning process. We focus on two problems related to how adaptation actions are explored. First, existing solutions randomly explore adaptation actions and thus may exhibit slow learning if there are many possible adaptation actions. Second, they are unaware of system evolution, and thus may explore new adaptation actions introduced during evolution rather late. We propose novel exploration strategies that use feature models (from software product line engineering) to guide exploration in the presence of many adaptation actions and system evolution. Experimental results for two realistic self-adaptive systems indicate an average speed-up of the learning process of 33.7% in the presence of many adaptation actions, and of 50.6% in the presence of evolution.

show abstract

“…Notably, we found only 13 concrete variables related to "Reliability." 9 For example, packed loss is used to assess reliability in [67]. The dependent variables refer mostly to the managed system (146 times, 55% of the total count) followed by both managing and managed system (57 times, 21%) and managing system (50 times, 19%).…”

Section: What Is the Experimental Design?mentioning

confidence: 99%

How do we Evaluate Self-adaptive Software Systems? [replication package]

Gerostathopoulos,

Vogel,

Weyns

et al. 2021

Self Cite

View full text Add to dashboard Cite

With the increase of research in self-adaptive systems, there is a need to better understand the way research contributions are evaluated. Such insights will support researchers to better compare new findings when developing new knowledge for the community. However, so far there is no clear overview of how evaluations are performed in self-adaptive systems. To address this gap, we conduct a mapping study. The study focuses on experimental evaluations published in the last decade at the prime venue of research in software engineering for self-adaptive systems-the International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS). Results point out that specifics of self-adaptive systems require special attention in the experimental process, including the distinction of the managing system (i.e., the target of evaluation) and the managed system, the presence of uncertainties that affect the system behavior and hence need to be taken into account in data analysis, and the potential of managed systems to be reused across experiments, beyond replications. To conclude, we offer a set of suggestions derived from our study that can be used as input to enhance future experiments in self-adaptive systems.

show abstract

Applying deep learning to reduce large adaptation spaces of self-adaptive systems with multiple types of goals

Cited by 33 publications

References 29 publications

Towards fuzzification of adaptation rules in self-adaptive architectures

Towards fuzzification of adaptation rules in self-adaptive architectures

Realizing self-adaptive systems via online reinforcement learning and feature-model-guided exploration

How do we Evaluate Self-adaptive Software Systems? [replication package]

Contact Info

Product

Resources

About