Self-adaptive Framework Research Articles

Multidisciplinary cancer disease classification using adaptive FL in healthcare industry 5.0

Emerging Industry 5.0 designs promote artificial intelligence services and data-driven applications across multiple places with varying ownership that need special data protection and privacy considerations to prevent the disclosure of private information to outsiders. Due to this, federated learning offers a method for improving machine-learning models without accessing the train data at a single manufacturing facility. We provide a self-adaptive framework for federated machine learning of healthcare intelligent systems in this research. Our method takes into account the participating parties at various levels of healthcare ecosystem abstraction. Each hospital trains its local model internally in a self-adaptive style and transmits it to the centralized server for universal model optimization and communication cycle reduction. To represent a multi-task optimization issue, we split the dataset into as many subsets as devices. Each device selects the most advantageous subset for every local iteration of the model. On a training dataset, our initial study demonstrates the algorithm's ability to converge various hospital and device counts. By merging a federated machine-learning approach with advanced deep machine-learning models, we can simply and accurately predict multidisciplinary cancer diseases in the human body. Furthermore, in the smart healthcare industry 5.0, the results of federated machine learning approaches are used to validate multidisciplinary cancer disease prediction. The proposed adaptive federated machine learning methodology achieved 90.0%, while the conventional federated learning approach achieved 87.30%, both of which were higher than the previous state-of-the-art methodologies for cancer disease prediction in the smart healthcare industry 5.0.

A Game-Theoretical Self-Adaptation Framework for Securing Software-Intensive Systems

Security attacks present unique challenges to the design of self-adaptation mechanism for software-intensive systems due to the adversarial nature of the environment. Game-theoretical approaches have been explored in security to model malicious behaviors and design reliable defense for the system in a mathematically grounded manner. However, modeling the system as a single player, as done in prior works, is insufficient for the system under partial compromise and for the design of fine-grained defensive policies where the rest of the system with autonomy can cooperate to mitigate the impact of attacks. To address such issues, we propose a new self-adaptation framework incorporating Bayesian game theory and model the defender (i.e., the system) at the granularity of components. Under security attacks, the architecture model of the system is automatically translated, by the proposed translation process with designed algorithms, into a multi-player Bayesian game. This representation allows each component to be modelled as an independent player, while security attacks are encoded as variant types for the components. By solving for pure equilibrium (i.e., adaptation response), the system’s optimal defensive strategy is dynamically computed, enhancing system resilience against security attacks by maximizing system utility. We validate the effectiveness of our framework through two sets of experiments using generic benchmark tasks tailored for the security domain. Additionally, we exemplify the practical application of our approach through a real-world implementation in the Secure Water Treatment System to demonstrates the applicability and potency in mitigating security risks.

Multi-Stream Concept Drift Self-Adaptation Using Graph Neural Network

Concept drift is the phenomenon where the data distribution in a data stream changes over time. It is a ubiquitous problem in the real-world, for example, a traffic accident would cause a jam in a certain period, leading to a distribution change in traffic speed. Most research in the concept drift field focuses on single data stream, however, few of them consider multi-stream environments which are more in line with the application needs. To fill this gap, we propose a multi-stream prediction setting and a multi-stream concept drift self-adaptation framework using graph neural network, named SAGN. In SAGN, we reconsider the learning procedure of GNN-based predictors from an aspect of concept drift adaptation for multi-stream. By this design, the prediction task is converted into online streaming data tasks in sub-graphs. Each sub-graph corresponds to an adaptation target and will be updated over time. In this way, locally we can overcome drift in each sub-graph by a designed adaptation technique, and globally the correlation between different data streams is well-preserved as a graph structure. Therefore, whether drift occurs or not, in one or several streams, SAGNcan provide consistently accurate prediction results. We comprehensively tested SAGNon both synthetic and real-world, drift and non-drift data in the multi-step prediction task. The experiment results show that SAGNis able to achieve state-of-the-art performance in most cases.

A model for automatic selection of IoT services in ambient assisted living for the elderly

Context:Engineering Ambient Assisted Living applications for the elderly is challenging due to the diversity and rapid changes of both end users’ needs and technological environment equipment. Objective:Assistive applications can be provided as combinations of functionalities provided by IoT devices. With the pervasive availability of functionally equivalent IoT devices, they should be selected according to the specific deployment context in terms of user needs and conditions, device availability, and regulations when the operative context dynamic conditions can be set. Such selection is the objective of this work. Methods:We rely on a conceptual framework for self-adaptation as the enabler for a run-time decision-making process. It allows for representing relations among IoT devices, the functionalities they deliver, and the different modalities these functionalities are provided with in terms of goals, devices, and norms. The framework is based on three fundamental principles: (1) high-level abstractions separating the expected functionality, how it can be delivered, and who is responsible for its delivery; (2) AAL applications as the run-time composition of atomic functionalities; (3) centrality of the user in the system. Result:The Device-Goal-Norm framework is proposed to specify diagrams for different AAL applications, together with the semantics to transform these diagrams into run-time models. We also provide a running implementation of a run-time model based on the belief–desire–intention paradigm.

Self-Adaptive Framework With Master–Slave Architecture for Internet of Things

The Internet of Things (IoT) connects a wide range of entities and can be applied to various types of environments. In addition, IoT environments can be dynamically changed at runtime; thus, IoT systems can be deployed in various environments. To support stable operation, IoT systems must adapt to dynamic environmental changes. The self-adaptive software aims to adjust various artifacts or attributes of software to adapt the detected context by itself, and various studies have applied self-adaptive methods in IoT-related research. In this study, we proposed a self-adaptive software framework with master–slave architecture-based finite-state machine modeling. In addition, model checking is applied, which is a formal method to verify IoT systems at runtime, and a cache-based mechanism is applied to reduce the computational time required for verification. To demonstrate the efficiency of the proposed framework, an empirical evaluation was performed with several model-checking tools (RINGA, NuSMV, nuXmv, and CadenceSMV), and the results showed the efficiency of the proposed framework with the cache-based mechanism. In addition, an example application was investigated with smart greenhouse scenarios, and the application was implemented on Android and Arduino. The application was operated in physical environments, and the results showed the practical usability of the proposed framework with verification at runtime.

Self-adaptation in smartphone applications: Current state-of-the-art techniques, challenges, and future directions

Context:In the last few years, smartphones have become an essential part of our lives. Several mobile applications have been uploaded to their respective app stores on daily basis to facilitate the end-users. To ensure the availability of the application and its services, the application needs to be able to detect and deal with various types of changes. Mobile application based self-adaptation is regarded as a solution to handle the above-mentioned chnages. Objective:The objectives of this study are: (i) identification of current state-of-the-art techniques, frameworks, models, and algorithms for self-adaptation in mobile applications context, (ii) exploring the core challenges faced in the development of self-adaptive mobile applications, and (iii) conducting a SWOT (Strength Weakness Opportunity Threat) analysis to figure out the research gaps in the targeted research field. Method:To accomplish the mentioned objective, we conducted a systematic literature review to enlighten the need for adaptation in this domain, the targeted areas, their beneficial aspects, state-of-the-art proposed solutions, and their challenges. We performed the keyword-based search on 11 well-known databases to determine the potential studies published between years 2015 to 2020. In total, 31 studies (from 933 potential studies) are selected grounded on the defined inclusion and exclusion criteria. Results:The main findings of this work are: (i) MAPE-K (Monitor Analyze Plan Execute-Knowledge) model is frequently used in several studies due to its resilience, (ii) current work focuses on the android operating system due to its popularity and flexibility; however, it lacks in considering other mobile’s operating systems, and (iii) reported work also lacks in mentioning any benchmark (self-adaptive framework). Conclusion:The current study is helpful for the researchers intended to work in the smartphones domain. From developers viewpoint, this study reports the faced challenges during the development of smartphones applications. Moreover, the performed study is beneficial in filling the identified research gaps by providing a foundation useful to plan future research regarding self-adaptation in smartphone applications context.

An autonomous performance testing framework using self-adaptive fuzzy reinforcement learning

Test automation brings the potential to reduce costs and human effort, but several aspects of software testing remain challenging to automate. One such example is automated performance testing to find performance breaking points. Current approaches to tackle automated generation of performance test cases mainly involve using source code or system model analysis or use-case-based techniques. However, source code and system models might not always be available at testing time. On the other hand, if the optimal performance testing policy for the intended objective in a testing process instead could be learned by the testing system, then test automation without advanced performance models could be possible. Furthermore, the learned policy could later be reused for similar software systems under test, thus leading to higher test efficiency. We propose SaFReL, a self-adaptive fuzzy reinforcement learning-based performance testing framework. SaFReL learns the optimal policy to generate performance test cases through an initial learning phase, then reuses it during a transfer learning phase, while keeping the learning running and updating the policy in the long term. Through multiple experiments in a simulated performance testing setup, we demonstrate that our approach generates the target performance test cases for different programs more efficiently than a typical testing process and performs adaptively without access to source code and performance models.

Programming framework and infrastructure for self-adaptation and optimized evolution method for microservice systems in cloud–edge environments

Edge computing technologies facilitate the deployment of services on nearby edge servers with a large number of end users and their mobile devices to fulfill personalized demands. Owing to frequent changes in user mobility and demands, service systems deployed in an edge–cloud environment must continuously adapt to ensure that the quality of service (QoS) perceived by the end users is maintained at a stable and satisfactory level. As it is difficult for system operation engineers to manually deal with such frequent and large-scale evolution due to problems of cost and efficiency, self-adaptation of the system is essential. In this paper, we present a programming framework for microservices (EPF4M) and an infrastructure for self-adaptive microservice systems (EI4MS) for the cloud–edge environment based on microservice architecture. Our study follows a “monitoring–analyzing–planning–execution” control loop that empowers the service systems to redeploy the services according to changes in the QoS. A two-phase strategy is adopted to minimize the side effects of the loop on the performance of the service system. A prototype of this framework and infrastructure has been open-sourced and verified through experiments conducted in a real cloud–edge environment. The results demonstrate the usefulness and advantages of our approach.

Toward a Self-Adaptive Cyberdefense Framework in Organization

Organizations suffer more than ever from the inability to securely manage the information system, despite their myriad efforts. By introducing a real cyberattack of a bank, this research analyzes the characteristics of modern cyberattacks and simulates the dynamic propagation that makes them difficult to manage. It develops a self-adaptive framework that through simulation, distinctly improves cyberdefense efficiency. The results illustrate the discrepancies of the previous studies and validate the use of a time-based self-adaptive model for cybersecurity management. The results further show the significance of human and organizational learning effects and a coordination mechanism in obtaining a highly dependable cyberdefense setting. This study also provides an illuminating analysis for humans to position themselves in the collaborations with increasingly intelligent agents in the future.

Distribution Network Reconfiguration based on LMP at DG connected busses using game theory and self-adaptive FWA

Distribution Company (DISCO) uses some price-based policies to maximize the profit of Distributed Generation (DG) owners and minimize the power loss of the network. Meanwhile, loss of the network is minimized by Distribution Network Reconfiguration (DNR). In this paper, a hybrid market-based DNR methodology is proposed to concurrently obtain both the optimal configuration of the network, and Locational Marginal Prices (LMPs) at DG connected busses. Firework Algorithm (FWA) is coupled with an Iterative Game-Based algorithm (IGBA) to procure the optimal configuration of the network with the objective of power loss minimization. In the hybrid methodology, through the search process of FWA in finding the optimal configuration, the IGBA is run for each candidate configuration. Using the IGBA, the LMPs of DG units is calculated based on their share of loss reduction which is determined by the game theory. Also, in the FW algorithm, improper selection of coefficients leads to inefficiency of the algorithm. Therefore, a self-adaptive framework is proposed to specify the value of coefficients during the evolution of algorithm. The effectiveness of the proposed methodology is evaluated using a practical system.

An enhanced teaching-learning-based optimization algorithm with self-adaptive and learning operators and its search bias towards origin

Abstract Teaching-learning-based optimization (TLBO) is a recently proposed meta-heuristic optimization method and demonstrates outstanding performance for solving numerous sciences and engineering problems. However, many studies have shown that TLBO has a strong bias towards converging to origin and poorly performs in the problems with shifted solutions. To conquer this problem, a novel self-adaptive hybrid self-learning based TLBO (SHSLTLBO) is proposed in this paper. By constructing a self-adaptive framework, the original TLBO is fused with the Gaussian distribution, and the novel updating law switches in two modes corresponding to the fitness during the searching process. Additionally, in order to avoid local convergence in the initialization, a self-learning phase is introduced, associated to the original teaching and learning phase. The performance of the proposed SHSLTLBO is tested in the numerical benchmark functions, where the comprehensive comparison carries out with the state-of-the-art TLBO variants and other meta-heuristic approaches. The results demonstrate superior advantages of the proposed algorithm at balancing along the evolutionary stages among the TLBO variants. In the experiments, the two well-performed meta-heuristic optimization methods, namely LSHADE and HCLPSO, are used as the comparative methods to SHSLTLBO, where their superior performances of them are shown on the shifted problems. With increasing dimensionality, the performance of TLBO goes down rapidly while LSHADE's relative ranking improves. Apart from these scenarios, the comparative results of different dimensional problems indicate that the proposed SHSLTLBO has the best convergence and stability in solving all 28 benchmarks with low dimension and shifted solutions.

Energy-Aware Self-Adaptation for Application Execution on Heterogeneous Parallel Architectures

Hardware in High Performance Computing environments in recent years have increasingly become more heterogeneous in order to improve computational performance. An additional aspect of such systems is the management of power and energy consumption. The increase in heterogeneity requires middleware and programming model abstractions to eliminate additional complexities that it brings, while also offering opportunities such as improved power management. In this paper, we explore application level self-adaptation including aspects such as automated configuration and deployment of applications to different heterogeneous infrastructure and for their redeployment. This therefore not only mitigates complexities associated with heterogeneous devices but aims to take advantage of the heterogeneity. The overall result of this paper is a self-adaptive framework that manages application Quality of Service (QoS) at runtime, which includes the automatic migration of applications between different accelerated infrastructures. Discussion covers when this migration is appropriate and quantifies the likely benefits.

Self-Adaptive Framework for Efficient Stream Data Classification on Storm

In this era of big data, stream data classification which is one of typical data stream applications has become more and more significant and challengeable. In these applications, it is obvious that data classification is much more frequent than model training. The ratio of stream data to be classified is rapid and time-varying, so it is an important problem to classify the stream data efficiently with high throughput. In this paper, we first analyze and categorize the current data stream machine learning algorithms according to their data structures. Then, we propose stream data classification topology (SDC-Topology) on Storm. For the classification algorithms based on the matrix, we propose self-adaptive stream data classification framework (SASDC-Framework) for efficient stream data classification on Storm. In SASDC-Framework, all the data sets arriving at the same unit time are partitioned into subsets with the nearly best partition size and processed in parallel. To select the nearly best partition size for the stream data sets efficiently, we adopt bisection method strategy and inverse distance weighted strategy. Extreme learning machine, which is a fast and accurate machine learning method based on matrix calculating, is used to test the efficiency of our proposals. According to evaluation results, the throughputs based on SASDC-Framework are 8–35 times higher than those based on SDC-Topology and the best throughput is more than 40000 prediction requests per second in our environment.

Improving the Dependability of Self-Adaptive Cyber Physical System With Formal Compositional Contract

To adapt to the uncertain environment smartly and timely, cyber physical systems (CPSs) have to interact with the physical world in a decentralized but rigorous, organized way. Guaranteeing the timing reliability is key to achieve consensus on the order of distributed events, as well as dependable cooperative decision processing. Based on our hierarchically decentralized compositional self-adaptive framework, we propose a formal compositional reliability-contract-based solution to guarantee the timing reliability of event observation and decision processing in a large-scale, geographically distributed CPS. As the prophetic decision may not fit the local situation well because of the uncertainties, we propose a gradual contract optimization solution to refine the dependability, timeliness, and energy consumption. Following the seven proposed composition schemes, we employ the nondominated sorting genetic algorithm II (NSGA-II) algorithm to optimize arrangement of decision. Moreover, a topology-aware time reserving solution is applied to improve the resilience of processing time and to tolerance timing failures. Both simulation results and real-world testing are introduced to evaluate the efficacy of our proposal. We believe that the formal compositional contract will be a competitive CPS solution to analyze requirements and optimize the self-adaptation decision at runtime.

Self-Adaptive Framework Based on MAPE Loop for Internet of Things.

The Internet of Things (IoT) connects a wide range of objects and the types of environments in which IoT can be deployed dynamically change. Therefore, these environments can be modified dynamically at runtime considering the emergence of other requirements. Self-adaptive software alters its behavior to satisfy the requirements in a dynamic environment. In this context, the concept of self-adaptive software is suitable for some dynamic IoT environments (e.g., smart greenhouses, smart homes, and reality applications). In this study, we propose a self-adaptive framework for decision-making in an IoT environment at runtime. The framework comprises a finite-state machine model design and a game theoretic decision-making method for extracting efficient strategies. The framework was implemented as a prototype and experiments were conducted to evaluate its runtime performance. The results demonstrate that the proposed framework can be applied to IoT environments at runtime. In addition, a smart greenhouse-based use case is included to illustrate the usability of the proposed framework.

CAMeL: A Self-Adaptive Framework for Enriching Context-Aware Middlewares with Machine Learning Capabilities

Context-aware middlewares support applications with context management. Current middlewares support both hardware and software sensors providing data in structured forms (e.g., temperature, wind, and smoke sensors). Nevertheless, recent advances in machine learning paved the way for acquiring context from information-rich, loosely structured data such as audio or video signals. This paper describes a framework (CAMeL) enriching context-aware middlewares with machine learning capabilities. The framework is focused on acquiring contextual information from sensors providing loosely structured data without the need for developers of implementing dedicated application code or making use of external libraries. Nevertheless the general goal of context-aware middlewares is to make applications more dynamic and adaptive, and the proposed framework itself can be programmed for dynamically selecting sensors and machine learning algorithms on a contextual basis. We show with experiments and case studies how the CAMeL framework can (i) promote code reuse and reduce the complexity of context-aware applications by natively supporting machine learning capabilities and (ii) self-adapt using the acquired context allowing improvements in classification accuracy while reducing energy consumption on mobile platforms.

Adaptive surrogate modeling with evolutionary algorithm for well placement optimization in fractured reservoirs

Well placement optimization is a decisive task for the reliable design of field development plans. The use of optimization routines coupled to reservoir simulation models as an automatic tool is a popular practice, which could improve the decision-making process on well placement problems. However, despite the various automatic techniques developed, there is still a lack of robust computer-added optimization tool, which can solve the well placement problem with high accuracy in reasonable time while handling the technical constraints properly. In this paper, a hybrid intelligent system is proposed to deal with a real well placement problem with arbitrary well trajectories, complex model grids, and linear and nonlinear constraints. In this intelligent approach, a Genetic Algorithm (GA) combined with a hybrid constraint-handling strategy is applied in conjunction with a constrained space-filling sampling design, Gaussian Process (GP) surrogate model, and one proposed adaptive sampling routine. This self-adaptive framework allows to consecutively augment the quality of surrogate, enhance the accuracy of the process, and thus guide the optimization rapidly into the optimal solution. To demonstrate the efficiency of the developed method, a full-field reservoir case is considered. This case covers a real well placement project in a fractured unconventional reservoir of El Gassi, which is a mature field located in Hassi-Massoud, Algeria. The obtained results highlighted the effectiveness of the proposed approach for solving the real well placement problem with high accuracy in reasonable CPU-time. These auspicious features make it a reliable tool to be used on other real optimization projects.

Smart and safe self‐adaption of connected devices based on discrete controllers

The Internet-of-things, which designates the interconnection of physical objects, is a growing research area with many challenges. One of these challenges is the management of failures and unforeseen situations when using connected devices in real world applications. To this end, the authors propose a self-adaptation framework to deal with changes and take into account storage, computational and communication constraints. Their self-adaptation framework relies on constraints expressed in terms of quality of service (QoS) and event-driven rules to specify control objectives. Internally, the framework generates labelled transitions systems and builds on the fly synchronous controllers to guarantee QoS properties. Moreover, their framework has capabilities to concurrently deal with dynamic control objectives, monitoring and self-adaptation. To prove the practicality of their framework, they present a healthcare case-study to remotely monitor a patient at risk of myocardial infarction recurrence. The objective control rules easily specify how wearable devices should coordinate their behaviours to ensure safety, resilience and health-awareness factors. The implementation of their framework is fully distributed and scalable and include their development of a wearable, remotely configurable, QoS aware cardiac activity sensor.

Guest Editorial: Adaptive and Reconfigurable Service‐Oriented, Cloud and Virtualised Architectures

The concept of adaptive and reconfigurable Service Oriented Architecture (SOA) has been introduced in order to describe architectures that exhibit emerging functional and non-functional properties in changing contexts. An adaptive and reconfigurable can repair itself if any execution problem occurs, in order to successfully complete its own execution, while respecting functional and non-functional agreements. In the design of an adaptive and reconfigurable SOA, several aspects have to be considered. For instance, the architecture components should be able to predict and to detect degradations and failures as soon as possible and to enact suitable recovery actions such as scaling-up and scaling-out of virtual execution resources. Moreover, different non-functional service-level requirements might be considered in order to complete the execution in case of a predicted imminent or observed occurring failure. Contributions are devoted to the design and the implementation of adaptive and reconfigurable and related Cloud applications. The issue contains five papers related to the foundations of SOA and Cloud and the tools and applications for and Cyber-Physical environments. Service Oriented Architecture and Cloud Computing E2SM: A Security tool for Adaptive Cloud-based Service-Oriented Applications by Takoua Abdellatif proposes an End-to-end Security Model (E2SM) that aims to protect data confidentiality in adaptive cloud-based applications. Whereas Leah Mutanu and Gerald Kotonya study the key factors that influence runtime adaptation in service-oriented architectures, and examines how well they are addressed in 29 adaptation approaches intended to support service-oriented systems in the paper entitled What, Where, When, How and Right of Runtime Adaptation in Service-Oriented Systems. The paper entitled and Analyzing Elastic Strategies in Cloud by Khaled Khebbeb et al. proposes a Bigraphical Reactive Systems based approach to provide a formal modelling of Cloud systems' structure using bigraphs, and their elastic behaviours using bigraphical reaction rules. Smart and Cyber-Physical environments and Verifying Time-aware Processes for Cyber-Physical Environments by Imen Graja et al. proposes to extend Business Process Modeling Notation to support the various Cyber-physical system concepts and properties. The paper entitled and Safe Self-Adaption of Connected Devices Based on Discrete Controllers by Arthur Gatouillat et al. proposes a self-adaptation framework to deal with changes and takes into account storage, computational and communication constraints.

A self-adaptation framework based on functional knowledge for augmented autonomy in robots

Robot control software endows robots with advanced capabilities for autonomous operation, such as navigation, object recognition or manipulation, in unstructured and dynamic environments. However, there is a steady need for more robust operation, where robots should perform complex tasks by reliably exploiting these novel capabilities. Mission-level resilience is required in the presence of component faults through failure recovery.To address this challenge, a novel self-adaptation framework based on functional knowledge for augmented autonomy is presented. A metacontroller is integrated on top of the robot control system,and it uses an explicit run-time model of the robot’s controller and its mission to adapt to operational changes. The model is grounded on a functional ontology that relates the robot’s mission with the robot’s architecture, and it is generated during the robot’s development from its engineering models. Advantages are discussed from both theoretical and practical viewpoints. An application example in a real autonomous mobile robot is provided. In this example, the generic metacontroller uses the robot’s functional model to adapt the control architecture to recover from a sensor failure.