Abstract The advent of edge computing holds immense promise for advancing the digitization of society, ushering in critical applications that elevate the overall quality of life. Yet, the practical implementation of the edge paradigm proves more challenging than anticipated, encountering disruptions primarily due to the constraints of applying conventional cloud‐based strategies at the network's periphery. Increasingly influenced by sustainability commitments, industry regulations currently view edge computing as a potential threat, primarily due to the energy inefficiency of solutions situated in close proximity to data generation sources and the rising density of computing. This paper presents a proactive strategy to transform the perceived threat into an opportunity, steering the sustainable evolution of future edge infrastructures to make them both environmentally and economically competitive for accelerated adoption. The vision outlined addresses key challenges associated with edge deployment and operation, emphasizing energy efficiency, fault‐tolerant automation, and collaborative orchestration. The proposed approach integrates two‐phase immersion cooling, formal modeling, machine learning, and federated management to effectively harness heterogeneity, propelling the sustainability of edge computing. To substantiate the efficacy of this approach, the paper details initial efforts towards establishing the sustainability of an edge infrastructure designed for an Advanced Driver Assistance Systems application.

The Cloud paradigm is at a critical point in which the existing energy-efficiency techniques are reaching a plateau, while the computing resources demand at Data Center facilities continues to increase exponentially. The main challenge in achieving a global energy efficiency strategy based on Artificial Intelligence is that we need massive amounts of data to feed the algorithms. This paper proposes a time-series data augmentation methodology based on synthetic scenario forecasting within the Data Center. For this purpose, we will implement a powerful generative algorithm: Generative Adversarial Networks (GANs). Specifically, our work combines the disciplines of GAN-based data augmentation and scenario forecasting, filling the gap in the generation of synthetic data in DCs. Furthermore, we propose a methodology to increase the variability and heterogeneity of the generated data by introducing on-demand anomalies without additional effort or expert knowledge. We also suggest the use of Kullback-Leibler Divergence and Mean Squared Error as new metrics in the validation of synthetic time series generation, as they provide a better overall comparison of multivariate data distributions. We validate our approach using real data collected in an operating Data Center, successfully generating synthetic data helpful for prediction and optimization models. Our research will help optimize the energy consumed in Data Centers, although the proposed methodology can be employed in any similar time-series-like problem.

Chronic diseases benefit of the advances on personalize medicine coming out of the integrative convergence of significant developments in systems biology, the Internet of Things and Artificial Intelligence. 70% to 80% of all healthcare costs in the EU and US are currently spent on chronic diseases, leading to estimated costs of C=700 billion and $3.5 trillion respectively. The management of symptomatic pain crises in chronic diseases is based on general clinical guidelines that do not take into account the singularities of the crises, such as their intensity or duration, so that the pain of those particular crises may cause the medication to be ineffective and lead the patient to overmedication. Knowing in detail the characteristics of the pain would help the physician to objectively prescribe personalized treatments for each patient and crisis. In this manuscript, we make a step further on the prediction of symptomatic crisis from ambulatory collected data in chronic diseases. We propose a categorization of pain types according to subjective symptoms of real patients. Our approach has been evaluated in the migraine disease. The migraine is one of the most disabling neurological diseases that affects over 12% of the population worldwide and leads to high economic costs for private and public health systems. This study aims to classify pain episodes by the characterization of pain curves reported by patients in real time. Pain curves have been described as a set of morphological features. With these features the pain episodes are clustered then classified by unsupervised and supervised machine learning models. It is shown that the evolution of different pain episodes in chronic diseases can be modeled and clustered. Over a population of 51 migraine patients, it has been found that there are 4 clusters of pain types that can be classified using 4 morphological features with an accuracy of 99.0% using a Logistic Model Tree algorithm.

Microarchitectural side channel attacks have been very prominent in security research over the last few years. Caches proved to be an outstanding side channel, as they provide high resolution and generic cross-core leakage. All major cryptographic libraries provide countermeasures to hinder key extraction via cross-core cache attacks by now. In this paper, we analyze implementations protected by prefetch-based countermeasures aimed at preventing well-known cache attacks, and highlight the circumstances causing them to remain vulnerable. Further, we craft a novel attack technique that precisely synchronizes the attacking and the victim processes, enabling the attacking process to evict the target data from the cache at the desired instants. One key improvement of our approach is that it provides unprivileged attackers with a method to remove specific data from the cache with a single memory access and in absence of shared memory by leveraging the transient capabilities of TSX and relying on the L3 replacement policy. We show the feasibility of our approach by extracting an RSA key from the latest wolfSSL library and an AES key from the T-Table and S-Box implementations included in OpenSSL with CacheSniper. Both libraries implement prefetch-based methods as a protection against cache attacks.

Until now, the reigning computing paradigm has been Cloud Computing, whose facilities concentrate in large and remote areas. Novel data-intensive services with critical latency and bandwidth constraints, such as autonomous driving and remote health, will suffer under an increasingly saturated network. On the contrary, Edge Computing brings computing facilities closer to end-users to offload workloads in Edge Data Centers (EDCs). Nevertheless, Edge Computing raises other concerns like EDC size, energy consumption, price, and user-centered design. This research addresses these challenges by optimizing Edge Computing scenarios in two ways, two-phase immersion cooling systems and smart resource allocation via Deep Reinforcement Learning. To this end, several Edge Computing scenarios have been modeled, simulated, and optimized with energy-aware strategies using real traces of user demand and hardware behavior. These scenarios include air-cooled and two-phase immersion-cooled EDCs devised using hardware prototypes and a resource allocation manager based on an Advantage Actor–Critic (A2C) agent. Our immersion-cooled EDC’s IT energy model achieved an NRMSD of 3.15% and an R2 of 97.97%. These EDCs yielded an average energy saving of 22.8% compared to air-cooled. Our DRL-based allocation manager further reduced energy consumption by up to 23.8% in comparison to the baseline.

Activity recognition, as an important component of behavioral monitoring and intervention, has attracted enormous attention, especially in Mobile Cloud Computing (MCC) and Remote Health Monitoring (RHM) paradigms. While recently resource constrained wearable devices have been gaining popularity, their battery life is limited and constrained by the frequent wireless transmission of data to more computationally powerful back-ends. This paper proposes an ultra-low power activity recognition system using a novel adaptive compressed sensing technique that aims to minimize transmission costs. Coarse-grained on-body sensor localization and unsupervised clustering modules are devised to autonomously reconfigure the compressed sensing module for further power saving. We perform a thorough heuristic optimization using Grammatical Evolution (GE) to ensure minimal computation overhead of the proposed methodology. Our evaluation on a real-world dataset and a low power wearable sensing node demonstrates that our approach can reduce the energy consumption of the wireless data transmission up to 81.2 and 61.5 percent, with up to 60.6 and 35.0 percent overall power savings in comparison with baseline and a naive state-of-the-art approaches, respectively. These solutions lead to an average activity recognition accuracy of 89.0 percent-only 4.8 percent less than the baseline accuracy-while having a negligible energy overhead of on-node computation.

In order to optimize the energy use of servers in Data Centers, techniques such as power capping or power budgeting are usually deployed. These techniques rely on the prediction of the power and execution time of applications. These data are obtained via dynamic profiling which requires a full execution of the application. This is not feasible in High Performance Computing (HPC) applications with long execution times. In this paper, we present a methodology to estimate the dynamic CPU and memory energy consumption of an application without executing it completely. Our methodology merges static code analysis information and dynamic profiling via the partial execution of the application. We do so by leveraging the concept of application signature, defined as a reduced version of the application in terms of execution time and power profile. We validate our methodology with a set of CPU -intensive, memory-intensive benchmarks and multi-threaded applications in a presently shipping enterprise server. Our energy estimation methodology shows an overall error below 8.0% when compared to the dynamic energy of the whole execution of the application. Also, our energy estimation methodology allows to estimate the energy of multi-threaded applications with an RMSE equal to 12.7% when compared to the dynamic energy from the complete parallel execution.

Summary Data centers handle impressive high figures in terms of energy consumption, and the growing popularity of cloud applications is intensifying their computational demand. Moreover, the cooling needed to keep the servers within reliable thermal operating conditions also has an impact on the thermal distribution of the data room, thus affecting to servers' power leakage. Optimizing the energy consumption of these infrastructures is a major challenge to place data centers on a more scalable scenario. Thus, understanding the relationship between power, temperature, consolidation, and performance is crucial to enable an energy‐efficient management at the data center level. In this research, we propose novel power and thermal‐aware strategies and models to provide joint cooling and computing optimizations from a local perspective based on the global energy consumption of metaheuristic‐based optimizations. Our results show that the combined awareness from both metaheuristic and best fit decreasing algorithms allow us to describe the global energy into faster and lighter optimization strategies that may be used during runtime. This approach allows us to improve the energy efficiency of the data center, considering both computing and cooling infrastructures, in up to a 21.74% while maintaining quality of service.

Wearable monitoring devices for ubiquitous health care are becoming a reality that has to deal with limited battery autonomy. Several researchers focus their efforts in reducing the energy consumption of these motes: from efficient micro-architectures, to on-node data processing techniques. In this paper we focus in the optimization of the energy consumption of monitoring devices for the prediction of symptomatic events in chronic diseases in real time. To do this, we have developed an optimization methodology that incorporates information of several sources of energy consumption: the running code for prediction, and the sensors for data acquisition. As a result of our methodology, we are able to improve the energy consumption of the computing process up to 90% with a minimal impact on accuracy. The proposed optimization methodology can be applied to any prediction modeling scheme to introduce the concept of energy efficiency. In this work we test the framework using Grammatical Evolutionary algorithms in the prediction of chronic migraines.

Summary Computational demand in data centers is increasing because of the growing popularity of Cloud applications. However, data centers are becoming unsustainable in terms of power consumption and growing energy costs so Cloud providers have to face the major challenge of placing them on a more scalable curve. Also, Cloud services are provided under strict Service Level Agreement conditions, so trade‐offs between energy and performance have to be taken into account. Techniques as Dynamic Voltage and Frequency Scaling (DVFS) and consolidation are commonly used to reduce the energy consumption in data centers, although they are applied independently and their effects on Quality of Service are not always considered. Thus, understanding the relationship between power, DVFS, consolidation, and performance is crucial to enable energy‐efficient management at the data center level. In this work, we propose a DVFS policy that reduces power consumption while preventing performance degradation, and a DVFS‐aware consolidation policy that optimizes consumption, considering the DVFS configuration that would be necessary when mapping Virtual Machines to maintain Quality of Service. We have performed an extensive evaluation on the CloudSim toolkit using real Cloud traces and an accurate power model based on data gathered from real servers. Our results demonstrate that including DVFS awareness in workload management provides substantial energy savings of up to 41.62% for scenarios under dynamic workload conditions. These outcomes outperforms previous approaches, that do not consider integrated use of DVFS and consolidation strategies.

The migraine disease is a chronic headache presenting symptomatic crisis that causes high economic costs to the national health services, and impacts negatively on the quality of life of the patients. Even if some patients can feel unspecific symptoms before the onset of the migraine, these only happen randomly and cannot predict the crisis precisely. In our work, we have proved how migraine crisis can be predicted with high accuracy from the physiological variables of the patients, acquired by a non-intrusive Wireless Body Sensor Network. In this paper, we derive alternative models for migraine prediction using Grammatical Evolution techniques. We obtain prediction horizons around 20 minutes, which are sufficient to advance the drug intake and avoid the symptomatic crisis. The robustness of the models with respect to sensor failures has also been tackled to allow the practical implementation in the ambulatory monitoring platform. The achieved models are non linear mathematical expressions with low computing overhead during the run-time execution in the wearable devices.

The increasing success of Cloud Computing applications and online services has contributed to the unsustainability of data center facilities in terms of energy consumption. Higher resource demand has increased the electricity required by computation and cooling resources, leading to power shortages and outages, specially in urban infrastructures. Current energy reduction strategies for Cloud facilities usually disregard the data center topology, the contribution of cooling consumption and the scalability of optimization strategies. Our work tackles the energy challenge by proposing a temperature-aware VM allocation policy based on a Trust-and-Reputation System (TRS). A TRS meets the requirements for inherently distributed environments such as data centers, and allows the implementation of autonomous and scalable VM allocation techniques. For this purpose, we model the relationships between the different computational entities, synthesizing this information in one single metric. This metric, called reputation, would be used to optimize the allocation of VMs in order to reduce energy consumption. We validate our approach with a state-of-the-art Cloud simulator using real Cloud traces. Our results show considerable reduction in energy consumption, reaching up to 46.16% savings in computing power and 17.38% savings in cooling, without QoS degradation while keeping servers below thermal redlining. Moreover, our results show the limitations of the PUE ratio as a metric for energy efficiency. To the best of our knowledge, this paper is the first approach in combining Trust-and-Reputation systems with Cloud Computing VM allocation.

Nowadays, data centers consume about 2% of the worldwide energy production, originating more than 43 million tons of CO2 per year. Cloud providers need to implement an energy-efficient management of physical resources in order to meet the growing demand for their services and ensure minimal costs. From the application-framework viewpoint, Cloud workloads present additional restrictions as 24/7 availability, and SLA constraints among others. Also, workload variation impacts on the performance of two of the main strategies for energy-efficiency in Cloud data centers: Dynamic Voltage and Frequency Scaling (DVFS) and Consolidation. Our work proposes two contributions: 1) a DVFS policy that takes into account the trade-offs between energy consumption and performance degradation; 2) a novel consolidation algorithm that is aware of the frequency that would be necessary when allocating a Cloud workload in order to maintain QoS. Our results demonstrate that including DVFS awareness in workload management provides substantial energy savings of up to 39.14% for scenarios under dynamic workload conditions.

The increasing demand for computational resources has led to a significant growth of data center facilities. A major concern has appeared regarding energy efficiency and consumption in servers and data centers. The use of flexible and scalable server power models is a must in order to enable proactive energy optimization strategies. This paper proposes the use of Evolutionary Computation to obtain a model for server dynamic power consumption. To accomplish this, we collect a significant number of server performance counters for a wide range of sequential and parallel applications, and obtain a model via Genetic Programming techniques. Our methodology enables the unsupervised generation of models for arbitrary server architectures, in a way that is robust to the type of application being executed in the server. With our generated models, we are able to predict the overall server power consumption for arbitrary workloads, outperforming previous approaches in the state-of-the-art.

The computational and cooling power demands of enterprise servers are increasing at an unsustainable rate. Understanding the relationship between computational power, temperature, leakage, and cooling power is crucial to enable energy-efficient operation at the server and data center levels. This paper develops empirical models to estimate the contributions of static and dynamic power consumption in enterprise servers for a wide range of workloads, and analyzes the interactions between temperature, leakage, and cooling power for various workload allocation policies. We propose a cooling management policy that minimizes the server energy consumption by setting the optimum fan speed during runtime. Our experimental results on a presently shipping enterprise server demonstrate that including leakage awareness in workload and cooling management provides additional energy savings without any impact on performance.

Reducing the energy consumption for computation and cooling in servers is a major challenge considering the data center energy costs today. To ensure energy-efficient operation of servers in data centers, the relationship among computational power, temperature, leakage, and cooling power needs to be analyzed. By means of an innovative setup that enables monitoring and controlling the computing and cooling power consumption separately on a commercial enterprise server, this paper studies temperature-leakage-energy tradeoffs, obtaining an empirical model for the leakage component. Using this model, we design a controller that continuously seeks and settles at the optimal fan speed to minimize the energy consumption for a given workload. We run a customized dynamic load-synthesis tool to stress the system. Our proposed cooling controller achieves up to 9% energy savings and 30W reduction in peak power in comparison to the default cooling control scheme.

Energy consumption in data centers is nowadays a critical objective because of its dramatic environmental and economic impact. Over the last years, several approaches have been proposed to tackle the energy/cost optimization problem, but most of them have failed on providing an analytical model to target both the static and dynamic optimization domains for complex heterogeneous data centers. This paper proposes and solves an optimization problem for the energy-driven configuration of a heterogeneous data center. It also advances in the proposition of a new mechanism for task allocation and distribution of workload. The combination of both approaches outperforms previous published results in the field of energy minimization in heterogeneous data centers and scopes a promising area of research.

Trust and reputation have been suggested as an effective security mechanism for open and distributed environments. However, even though there exists a high number of identified attacks against Trust and Reputation Systems (TRS), a generic security framework to identify all of them in a holistic way has not yet been proposed. This work presents a TRS attack taxonomy based on an TRS architectural model and a set of well-known security topics. Based on this taxonomy, two main deficiencies of the state-of-the-art in TRS security literature are detected: the existence of TRS attacks that have received few attention from the TRS community despite its importance, and potential threats that have not been previously identified. Finally, a real-life TRS scenario is analyzed as a proof-of-concept of the proposed taxonomy.

Along with the development of cognitive radio networks, designing optimistic security mechanisms is becoming a big challenge. This study proposes a taxonomy of attacks on cognitive radio networks. This will help researches to better understand the security problems and to design more optimistic countermeasures. A new simulation framework for security threats has been developed to check all these attacks and countermeasures. The simulation framework has been tested with a primary user emulation attack. A new testbed for simulations suitable for cognitive radio security is ready.

In this article we propose to couple reputation systems for wireless sensor networks with a genetic algorithm in order to improve their time of response to adversarial activities. The reputation of each node is assigned by an unsupervised genetic algorithm trained for detecting outliers in the data. The response of the system consists in assigning low reputation values to the compromised nodes cutting them off from the rest of the network. The genetic algorithm uses the feature extraction process that does not capture the properties of the attacks, but rather relies on the existing temporal and spatial redundancy in sensor networks and tries to detect temporal and spatial inconsistencies in the sequences of sensed values and the routing paths used to forward these values to the base station. This solution offers many benefits: scalable solution, fast response to thwart activities, ability to detect unknown attacks, high adaptability, and high ability in detecting and confining attacks. Comparing to the standard clustering algorithms, the benefit of this one is that it is not necessary to assign the number of clusters from the beginning. The solution is also robust to both parameter changes and the presence of large amounts of malicious data in the training and testing datasets.

The most serious obstacle in further proliferation of wireless sensor networks is their low level of security, where the insider attacks are the most challenging issue. In this work we propose a holistic solution for detecting and confining insider attacks that couples reputation systems with clustering techniques, namely unsupervised genetic lgorithm and self-organizing maps, trained for detecting outliers in data. The novelty of this work is the redundancy in detecting agents, their evaluation based on the majority voting and the calculation of the reputation as the average value, which makes it more robust to different attack scenarios and their parameter variations. The algorithms use the feature space based on sequences of sensor outputs (both temporal and spatial), as well as the routing paths used to forward the data to the base station, and designed with the idea of introducing the ability to detect a wide range of attacks. The solution performs both attack detection and recovery from attacks, and it offers many benefits: scalable solution, fast response to adversarial activities, ability to detect unknown attacks, high adaptability and high ability in detecting and confining attacks.

Summary form only given. Current embedded systems are made of multiple heterogeneous devices interconnected. These devices present a great variation of functionality, performance, and interfaces. Therefore, it is difficult to build applications for these platforms. In this paper we present some techniques to introduce component-based methodologies into hardware-software codesign. We place special emphasis on the use of simple, homogeneous interfaces to hide the inherent complexity of current designs. A key contribution is the definition of a HW-SW Operating System that makes system resources available to application developers in a clean, homogeneous way. This greatly simplifies the task of designing complex heterogeneous embedded systems.

Presents a new specification technique for complex hardware-sofware systems, based on standard high-level programming languages, such as C, C++, Java, Scheme, or Ada, without extensions or semantic changes. Unlike previous approaches, the designer may choose the model of computation and the specification language that best suits her needs, while still being able to formally verify the correctness of the specification. The details of the available hardware and software resources, and the implementation of the different models of computation are encapsulated in libraries to maximize reuse in system specifications.