Search

Communication networks and systems are continuously threatened by a great variety of cybersecurity attacks coming from new malware that targets old and new systems’ vulnerabilities. In this sense, Intrusion Detection Systems (IDSs) and, specifically, Network IDSs (NIDSs) are used to count on robust methods and techniques to detect and classify security attacks. One of the important parts in the assessment of NIDSs, is the Feature Engineering (FE) process, where raw datasets are transformed onto derived ones where both, features and observations are smartly transformed. In this work, the ff4ml framework, which includes the Feature as a Counter (FaaC) FE approach, is used to transform raw features into new ones that are counters of the originals. The FaaC approach aggregates raw observations by time intervals, thus limiting its use to network datasets containing timestamps. This work proposes a batch-based aggregation technique that allows applying FaaC in timestamp-less datasets and analyzes its impact on the performance of Machine Learning (ML)-based NIDSs in comparison to timestamp-based aggregation approaches.

The study of dynamic multi-objective optimization problems (DMOP) is an area that has recently been receiving increased attention from researchers. Within the literature, various alternatives have been proposed to solve DMOPs, among them are the dynamic multi-objective evolutionary algorithms (DMOEA), which use stochastic methods to obtain solutions close to the optimum. With the constant proposal of new DMOPs with different challenges and properties, as well as DMOEAs to solve them, the issue of determining which alternatives are adequate for each problem arises. Hyper-heuristics are methodologies that use multiple heuristics to solve a problem. This allows them to effectively cover a wider spectrum of characteristics of optimization problems. This advantage also involves DMOPs, since a suitable hyper-heuristic can satisfactorily solve a greater number of problems compared to DMOEAs used individually. This paper presents a guide, as well as a checklist to support researchers in the design of hyper-heuristics to solve DMOPs using DMOEAs as their heuristics. This work also presents two case studies which include state-of-the-art proposals that follow each step of the proposed guide, the obtained results were efficient and satisfactory, which shows the effectiveness of this guide.

Particle Swarm Optimization algorithms (or PSO) have been widely studied in the Literature. It is known that they provide highly competitive results. However, they suffer from fast convergence to local optima. There exist works proposing the swarm decentralization by including some specific topologies in order to deal with this problem. These approaches highly improve the results. In this work, we propose PSO-CO, a PSO algorithm able to reduce the exploitation of the algorithm by introducing the concept of coalitions in the swarm. There is one leader in each of these coalitions, so that the particles belonging to a coalition are only influenced by their local leader, and not the global one. This mechanism allows different coalitions to explore different parts of the search space, reducing thus the convergence speed and enhancing the exploration capabilities of the algorithm. Moreover, the particles can leave a coalition and join another, facilitating the exchange of information between coalitions. For testing the efficiency of the proposed PSO-CO, we have chosen a relevant benchmark in the literature, specially designed for continuous optimization. Results show that PSO-CO highly improves the results obtained compared to classical PSO.

In this chapter, an analytical parameter tuning for the Archive Multi-Objective Simulated Annealing (AMOSA) with a fuzzy logic controller is proposed. The analytical tuning is used to compute the initial and final temperature, as well as the maximum metropolis length. The fuzzy logic controller is used to adjust the metropolis length for each temperature. These algorithms are used to solve the Heterogeneous Computing Scheduling Problem. The tuned AMOSA with a fuzzy logic controller is compared against an AMOSA without tuning. Three quality indicators are used to compare the performance of the algorithms, these quality indicators are hypervolume, generational distance, and generalized spread. The experimental results show that the tuned AMOSA with fuzzy logic controller achieves the best performance.

Plug-in hybrid (PH) buses offer range and operating flexibility of buses with conventional internal combustion engines with environmental. However, when they are frequently charged, they also enable societal benefits (emissions- and noise-related) associated with electric buses. Thanks to geofencing, pure electric drive of PH buses can be assigned to specific locations via a back-office system. As a result, PH buses not only can fulfil zero-emission (ZE) zones set by city authorities, but they can also minimize total energy use thanks to selection of locations favouring (from energy perspective) electric drive. Such a location-controlled behaviour allows executing targeted air quality improvement and noise reduction strategies as well reducing energy consumption. However, current ZE zone assignment strategies used by PH buses are static—they are based on the first-come-first serve rule and do not consider traffic conditions. In this article, we propose a novel recommendation system, based on artificial intelligence, that allows PH buses operating efficiently in a dynamic environment, making the best use of the available resources so that emission- and noise-pollution levels are minimized.

Several previous works have shown how using prior knowledge within machine learning models helps to overcome the curse of dimensionality issue in high dimensional settings. However, most of these works are based on simple linear models (or variations) or do make the assumption of knowing a pre-defined variable grouping structure in advance, something that will not always be possible. This paper presents a hybrid genetic algorithm and machine learning approach which aims to learn variables grouping structure during the model estimation process, thus taking advantage of the benefits introduced by models based on problem-specific information but with no requirement of having a priory any information about variables structure. This approach has been tested on four synthetic datasets and its performance has been compared against two well-known reference models (LASSO and Group-LASSO). The results of the analysis showed how that the proposed approach, called GAGL, considerably outperformed LASSO and performed as well as Group-LASSO in high dimensional settings, with the added benefit of learning the variables grouping structure from data instead of requiring this information a priory before estimating the model.

Dynamic optimization problems have attracted the attention of researchers due to their wide variety of challenges and their suitability for real-world problems. The application of hyper-heuristics to solve optimization problems is another area that has gained interest recently. These algorithms can apply a search space exploration method at different stages of the execution for finding high quality solutions. However, most of the proposed works using these methodologies do not focus on the development of hyper-heuristics for dynamic optimization problems. Despite that, they arise as very appropriate methods for dynamic problems, being highly responsive and able to quickly adapt to any possible changes in the problem environment. In this paper, we present a brief study of the most salient previously proposed hyper-heuristics to solve dynamic optimization problems, and classify them, taking into consideration the complexity of their low-level heuristics. Then, we identify some the most important research areas that have been vaguely explored in the Literature yet.

This work addresses the multi-objective resource provisioning problem for building cloud-based CDNs. The optimization objectives are the minimization of VM, network and storage cost, and the maximization of the QoS for the end-user. A brokering model is proposed such that a single cloud-based CDN is able to host multiple content providers applying a resource sharing strategy. Following this model, an offline multiobjective evolutionary approach is applied to optimize resource provisioning while a greedy heuristic is proposed for addressing online routing of content. Experimental results indicate the proposed approach may reduce total costs by up to 10.6% while maintaining high QoS values.

Literature reveals that optimization algorithms are generally composed of a large number of parameters that highly influence on its performance. In the early stages of the definition of a new algorithm, it is crucial to know how the uncertainty in the input parameters affects the behavior of the algorithm, influencing on its final output, so that it is possible to set up the most efficient configuration.

MANETs are specially vulnerable against security attacks. For protecting them, security solutions are traditionally addressed by the so-called intrusion detection and response systems. Nevertheless, using reactive (response) solutions, once the attack is detected, rely in long attack mitigation times. In this work, we propose the use of relay node placement techniques as proactive security solutions. Preliminary experimentation demonstrates the suitability and feasibility of such approaches, not only in reducing the attack mitigation time but in replacing detection and response based traditional solutions.

Sensitivity analysis is a mathematical tool that distributes the uncertainty of the output of a model among its different input variables. We use in this work the Extended Fourier Amplitude Sensitivity Test to carefully analyze the impact of 54 LLVM code optimization operators on the execution time of nine benchmark software programs. Experiments presented involve performing over 16 million executions. The results show that the different LLVM transformations have a low direct effect on the execution time, but it becomes meaningful when considering the transformation in combination with the others (almost 60% average impact by all passes on all considered benchmarks). These results provide slight indications on the transformations to apply for optimizing the software, revealing the extreme difficulty of the problem.

This article presents and evaluates twenty-four novel bi-objective efficient heuristics for the simultaneous optimization of makespan and robustness in the context of the static robust tasks mapping problem for datacenters. The experimental analysis compares the proposed methods over realistic problem scenarios. We study their accuracy, as well as the regions of the search space they explore, by comparing versus state-of-the-art Pareto fronts, obtained with four different specialized versions of well-known multi-objective evolutionary algorithms.

Support vector machines are widely used for classification and regression tasks. However, sequential implementations for support vector machines are usually unable to deal with the increasing size of current real-world learning problems. In this context, Intel®Xeon PhiTM processors allow easily incorporating high performance computing strategies to improve execution times. This article proposes a parallel implementation of the popular LIBSVM library, specially adapted to the Intel®Xeon PhiTM architecture. The proposed implementation is evaluated using publicly available datasets corresponding to classification and regression tasks. Results show that the proposed parallel version computes the same results than the original LIBSVM while reducing the time needed for training by up to a factor of 4.81.

This chapter analyzes the use of adaptive neighborhoods based on coalitions in evolutionary optimization frameworks. First, we introduce the concepts of evolutionary algorithms, population topologies and coalitions. We integrate all these topics to study how to avoid some of the drawbacks of previous evolutionary algorithms and to remove their typically required parameters. The main contribution of the chapter is a redefinition of the Evolutionary Algorithm with Coalitions (EACO), which uses cellular approaches with neighborhoods, allowing the formation of coalitions among cells as a way to create islands of evolution in order to preserve diversity. This idea speeds up the evolution of individuals grouped in high-quality coalitions that are quickly converging to promising solutions. In the results section, we successfully compare EACO with a canonical cGA (Cellular Genetic Algorithm), and provide evidences about the statistical significance of our results. We also analyze the influence of parameters in order to tune them up accordingly; and finally, we evaluate the performance of EACO under different complex network topologies.

This chapter presents a new kind of cloud brokering model called virtual broker. The virtual broker owns and manages what we call a virtual cloud, composed by a set of reserved VMs from a number of public cloud providers. This new broker sublets its resources to its customers as on-demand VMs, at lower prices than those offered in the market. This model is feasible because of the large price difference between on-demand and reserved VMs in current pricing schemes. We propose a number of online and offline heuristics to efficiently manage the resources of the virtual broker in order to optimize its revenue, as well as the QoS level offered to the customers. Two realistic versions of the problem are proposed and analyzed. The results show the proposed brokering model is a profitable business model for both the virtual broker and the cloud customers, reducing cloud customer costs down to 80% when compared to traditional on-demand renting costs.

This article presents a multiobjective approach for scheduling large workflows in distributed datacenters. We consider a realistic scheduling scenario of distributed cluster systems composed of multi-core computers, and a multi-objective formulation of the scheduling problem to minimize makespan, energy consumption and deadline violations. The studied schedulers follow a two-level schema: in the higher-level, we apply a multiobjective heuristic and a multiobjective metaheuristic, to distribute jobs between clusters; in the lower-level, specific backfilling-oriented scheduling methods are used for task scheduling locally within each cluster, considering precedence constraints. A new model for energy consumption in multi-core computers is applied. The experimental evaluation performed on a benchmark set of large workloads that model different realistic high performance computing applications demonstrates that the proposed multiobjective schedulers are able to improve both the makespan and energy consumption of the schedules when compared with a standard Optimistic Load Balancing Round Robin approach.

This chapter is focused on the problem of scheduling independent tasks on heterogeneous machines. The main contributions of our work are the following: a linear programming model to compute energy consumption for the execution of independent tasks on heterogeneous clusters, a constructive heuristic based on local search, and a new benchmark set. To assess our approach we compare the performance of two solution methods: a memetic algorithm, based on population search and local search, and a seeded genetic algorithm, based on NSGA-II. A Wilcoxon rank-sum test shows significant differences in the diversity of solutions found but not in hypervolume. The memetic algorithm gets the best diversity for a bigger instance set from the state of the art.

The multi-objective optimization methods are traditionally based on Pareto dominance or relaxed forms of dominance in order to achieve a representation of the Pareto front. However, the performance of traditional optimization methods decreases for those problems with more than three objectives to optimize. The decomposition of a multi-objective problem is an approach that transforms a multi-objective problem into many single-objective optimization problems, avoiding the need of any dominance form. This chapter provides a short review of the general framework, current research trends and future research topics on decomposition methods.

A Self-organizing Map (SOM) is a competitive learning neural network architecture that make available a certain amount of classificatory neurons, which self-organize spatially based on input patterns. In this paper we explore the use of complex network topologies, like small-world, scale-free or random networks; for connecting the neurons within a SOM, and apply them for Time Series Prediction (TSP).We follow the classical VQTAMmodel for function prediction, and consider several benchmarks to evaluate the quality of the predictions. The results presented in this work suggest that the most regular the network topology is, the better results it provides in prediction. Besides, we have found that not updating all the cells at the same time provides much better results.