Alberto Robles-Enciso
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Alberto Robles-Enciso has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Antonio Fernando Gomez Skarmeta
Department of Information and Communications Engineering, Faculty of Computer Science, University of Murcia, 30100 Murcia, Spain
7 shared publications - Ricardo Robles-Enciso
Information Technologies and Communications Department, Universidad Politcnica de Cartagena, Cartagena, Spain
3 shared publications - Alejandro Molina Zarca
Department of Information Technologies and Telecommunications, University Center of Defense at the Spanish Air Force Academy, San Javier, Spain
2 shared publications Antonio F. Skarmeta
2 shared publications- Dan Garcia-Carrillo
Odin Solutions SL,Murcia,Spain
1 shared publication - Jorge Bernal Bernabe
Department of Information and Communications Engineering, University of Murcia, Murcia, Spain
1 shared publication
Latest Publications
- Open Access
- 28 December 2024
- Published by Springer Nature in Journal of Network and Systems Management
- Vol. 33 (1) , 1-28
Dynamic Multi-Method Allocation for Intent-based Security Orchestration
- 28 December 2024
- Published by Springer Nature in Journal of Network and Systems Management
- Vol. 33 (1) , 1-28
Open AccessDynamic Multi-Method Allocation for Intent-based Security Orchestration
- Open Access
- 29 October 2024
- Published by MDPI AG in Smart Cities
- Vol. 7 (6) , 3210-3240
An Adaptive Energy Orchestrator for Cyberphysical Systems Using Multiagent Reinforcement Learning
Reducing carbon emissions is a critical issue for the near future as climate change is an imminent reality. To reduce our carbon footprint, society must change its habits and behaviours to optimise energy consumption, and the current progress in embedded systems and artificial intelligence has the potential to make this easier. The smart building concept and intelligent energy management are key points to increase the use of renewable sources of energy as opposed to fossil fuels. In addition, cyber-physical systems (CPSs) provide an abstraction of the management of services that allows the integration of both virtual and physical systems in a seamless control architecture. In this paper, we propose to use multiagent reinforcement learning (MARL) to model the CPS services control plane in a smart house, with the purpose of minimising, by shifting or shutdown services, the use of non-renewable energy (fuel generator) by exploiting solar production and batteries. Furthermore, our proposal dynamically adapts its behaviour in real time according to current and historic energy production, thus being able to handle occasional changes in energy production due to meteorological phenomena or unexpected energy consumption. In order to evaluate our proposal, we have developed an open-source smart building energy simulator and deployed our use case. Finally, several simulations with different configurations are evaluated to verify the performance. The simulation results show that the reinforcement learning solution outperformed the priority-based and the heuristic-based solutions in both power consumption and adaptability in all configurations.
- 29 October 2024
- Published by MDPI AG in Smart Cities
- Vol. 7 (6) , 3210-3240
Open AccessAn Adaptive Energy Orchestrator for Cyberphysical Systems Using Multiagent Reinforcement Learning
Reducing carbon emissions is a critical issue for the near future as climate change is an imminent reality. To reduce our carbon footprint, society must change its habits and behaviours to optimise energy consumption, and the current progress in embedded systems and artificial intelligence has the potential to make this easier. The smart building concept and intelligent energy management are key points to increase the use of renewable sources of energy as opposed to fossil fuels. In addition, cyber-physical systems (CPSs) provide an abstraction of the management of services that allows the integration of both virtual and physical systems in a seamless control architecture. In this paper, we propose to use multiagent reinforcement learning (MARL) to model the CPS services control plane in a smart house, with the purpose of minimising, by shifting or shutdown services, the use of non-renewable energy (fuel generator) by exploiting solar production and batteries. Furthermore, our proposal dynamically adapts its behaviour in real time according to current and historic energy production, thus being able to handle occasional changes in energy production due to meteorological phenomena or unexpected energy consumption. In order to evaluate our proposal, we have developed an open-source smart building energy simulator and deployed our use case. Finally, several simulations with different configurations are evaluated to verify the performance. The simulation results show that the reinforcement learning solution outperformed the priority-based and the heuristic-based solutions in both power consumption and adaptability in all configurations.
- Open Access
- 29 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 104102-104114
Adapting Containerized Workloads for the Continuum Computing
Container and microservices management platforms are currently one of the most important tools for cloud computing, but since the scope of these tools is homogeneous cloud architectures they have serious limitations in adapting to new computing paradigms. Therefore, using the default scheduler in heterogeneous node systems faces significant limitations when tasked with orchestrating workloads in a Continuum Computing environment, as the nodes have very different characteristics and restrictions. To solve this limitation we decided to use Kubernetes as it is the most popular Container management tool and we propose to replace the native scheduler with a reimplementation that gives us complete flexibility for the process of assigning pods to nodes, providing a framework to design algorithms that considers all the necessary parameters for the deployment of services in a Continuum. In addition, we address one of the most limiting aspects of the K8s scheduler, its pod-by-pod allocation approach, which makes it difficult to optimise the complete set of allocations. To test our proposal we design a use case and perform several tests on a real environment based on virtual machines, in which stress tests are conducted to measure the performance of each method. We then present a series of results to justify the benefits of our proposal, including the reduced performance provided by the pod-pod approach and how a batch-based approach greatly improves efficiency. The results show the usefulness of using batch-based approaches and how the Kubernetes scheduler extension points are not enough to support the requirements of the Continuum.
- 29 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 104102-104114
Open AccessAdapting Containerized Workloads for the Continuum Computing
Container and microservices management platforms are currently one of the most important tools for cloud computing, but since the scope of these tools is homogeneous cloud architectures they have serious limitations in adapting to new computing paradigms. Therefore, using the default scheduler in heterogeneous node systems faces significant limitations when tasked with orchestrating workloads in a Continuum Computing environment, as the nodes have very different characteristics and restrictions. To solve this limitation we decided to use Kubernetes as it is the most popular Container management tool and we propose to replace the native scheduler with a reimplementation that gives us complete flexibility for the process of assigning pods to nodes, providing a framework to design algorithms that considers all the necessary parameters for the deployment of services in a Continuum. In addition, we address one of the most limiting aspects of the K8s scheduler, its pod-by-pod allocation approach, which makes it difficult to optimise the complete set of allocations. To test our proposal we design a use case and perform several tests on a real environment based on virtual machines, in which stress tests are conducted to measure the performance of each method. We then present a series of results to justify the benefits of our proposal, including the reduced performance provided by the pod-pod approach and how a batch-based approach greatly improves efficiency. The results show the usefulness of using batch-based approaches and how the Kubernetes scheduler extension points are not enough to support the requirements of the Continuum.
- 14 December 2023
- Published by Springer Nature
- p. 100-114
Multi-agent Reinforcement Learning-Based Energy Orchestrator for Cyber-Physical Systems
- 14 December 2023
- Published by Springer Nature
- p. 100-114
Multi-agent Reinforcement Learning-Based Energy Orchestrator for Cyber-Physical Systems
- Open Access
- 21 November 2022
- Published by Elsevier in Computer Networks
- Vol. 220
A multi-layer guided reinforcement learning-based tasks offloading in edge computing
- 21 November 2022
- Published by Elsevier in Computer Networks
- Vol. 220
Open AccessA multi-layer guided reinforcement learning-based tasks offloading in edge computing
- 1 January 2022
- Published by Springer Nature
- p. 82-95
Task Offloading in Computing Continuum Using Collaborative Reinforcement Learning
- 1 January 2022
- Published by Springer Nature
- p. 82-95
Task Offloading in Computing Continuum Using Collaborative Reinforcement Learning
- Open Access
- 30 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 107137-107148
Architecture for Orchestrating Dynamic DNN-Powered Image Processing Tasks in Edge and Cloud Devices
DNN processing on image streams has opened the possibility for new and innovative applications. Some of those would benefit from performing the computation locally, avoiding incurring into latencies due to data travelling to image processing services in the cloud, and thus allowing for faster response times. New devices like the GPU-accelerated NVIDIA Jetson family, such as the Jetson Nano, are capable of running modern DNN image processing models, offering an affordable, powerful and scalable local alternative to cloud processing. Performing local image processing can also benefit security and even GDPR compliance, potentially easing the deployment of this solutions. Not only that, but local image processing can also bring the possibility of applying these techniques in areas with reduced connectivity, where cloud-based solutions are unfeasible. In this work, we propose an architecture for the orchestration of DNN accelerated image processing on IoT devices, based on FogFlow; an orchestration platform capable of leveraging cloud and edge resources. FogFlow is part of the FIWARE initiative and is based in the NGSI family of standards, widely applied in Smart City, Smart Building and Smart Home solutions, making it an easy-to-integrate technology.
- 30 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 107137-107148
Open AccessArchitecture for Orchestrating Dynamic DNN-Powered Image Processing Tasks in Edge and Cloud Devices
DNN processing on image streams has opened the possibility for new and innovative applications. Some of those would benefit from performing the computation locally, avoiding incurring into latencies due to data travelling to image processing services in the cloud, and thus allowing for faster response times. New devices like the GPU-accelerated NVIDIA Jetson family, such as the Jetson Nano, are capable of running modern DNN image processing models, offering an affordable, powerful and scalable local alternative to cloud processing. Performing local image processing can also benefit security and even GDPR compliance, potentially easing the deployment of this solutions. Not only that, but local image processing can also bring the possibility of applying these techniques in areas with reduced connectivity, where cloud-based solutions are unfeasible. In this work, we propose an architecture for the orchestration of DNN accelerated image processing on IoT devices, based on FogFlow; an orchestration platform capable of leveraging cloud and edge resources. FogFlow is part of the FIWARE initiative and is based in the NGSI family of standards, widely applied in Smart City, Smart Building and Smart Home solutions, making it an easy-to-integrate technology.
- Open Access
Security Architecture for Defining and Enforcing Security Profiles in DLT/SDN-Based IoT Systems
Despite the advantages that the Internet of Things (IoT) will bring to our daily life, the increasing interconnectivity, as well as the amount and sensitivity of data, make IoT devices an attractive target for attackers. To address this issue, the recent Manufacturer Usage Description (MUD) standard has been proposed to describe network access control policies in the manufacturing phase to protect the device during its operation by restricting its communications. In this paper, we define an architecture and process to obtain and enforce the MUD restrictions during the bootstrapping of a device. Furthermore, we extend the MUD model with a flexible policy language to express additional aspects, such as data privacy, channel protection, and resource authorization. For the enforcement of such enriched behavioral profiles, we make use of Software Defined Networking (SDN) techniques, as well as an attribute-based access control approach by using authorization credentials and encryption techniques. These techniques are used to protect devices’ data, which are shared through a blockchain platform. The resulting approach was implemented and evaluated in a real scenario, and is intended to reduce the attack surface of IoT deployments by restricting devices’ communication before they join a certain network.
Open AccessSecurity Architecture for Defining and Enforcing Security Profiles in DLT/SDN-Based IoT Systems
Despite the advantages that the Internet of Things (IoT) will bring to our daily life, the increasing interconnectivity, as well as the amount and sensitivity of data, make IoT devices an attractive target for attackers. To address this issue, the recent Manufacturer Usage Description (MUD) standard has been proposed to describe network access control policies in the manufacturing phase to protect the device during its operation by restricting its communications. In this paper, we define an architecture and process to obtain and enforce the MUD restrictions during the bootstrapping of a device. Furthermore, we extend the MUD model with a flexible policy language to express additional aspects, such as data privacy, channel protection, and resource authorization. For the enforcement of such enriched behavioral profiles, we make use of Software Defined Networking (SDN) techniques, as well as an attribute-based access control approach by using authorization credentials and encryption techniques. These techniques are used to protect devices’ data, which are shared through a blockchain platform. The resulting approach was implemented and evaluated in a real scenario, and is intended to reduce the attack surface of IoT deployments by restricting devices’ communication before they join a certain network.