Biblio

Fog computing plays a critical role in the provisioning of computing tasks in the context of Internet of Things (IoT) services. However, the security of IoT services against breaches and attacks relies heavily on the security of fog resources, which must be properly implemented and managed. Increasing security investments and integrating the security aspect into the core processes and operations of fog computing including resource management will increase IoT service protection as well as the trustworthiness of fog service providers. However, this requires careful modeling of the security requirements of IoT services as well as theoretical and experimental evaluation of the tradeoff between security and performance in fog infrastructures. To this end, this paper explores a new model for fog resource allocation according to security and Quality of Service (QoS). The problem is modeled as a multi-objective linear optimization problem and solved using conventional, off-the-shelf optimizers by applying the preemptive method. Specifically, two objective functions were defined: one representing the satisfaction of the security design requirements of IoT services and another that models the communication delay among the different virtual machines belonging to the same service request, which might be deployed on different intermediary fog nodes. The simulation results show that the optimization is efficient and achieves the required level of scalability in fog computing. Moreover, a tradeoff needs to be pondered between the two criteria during the resource allocation process.

In Particle Swarm Optimization Algorithm (PSO), the learning factors \$c\_1\$ and \$c\_2\$ are used to update the speed and location of a particle. However, the setting of those two important parameters has great effect on the performance of the PSO algorithm, which has limited its range of applications. To avoid the tedious parameter tuning, we introduce a transfer learning based adaptive parameter setting strategy to PSO in this paper. The proposed transfer learning strategy can adjust the two learning factors more effectively according to the environment change. The performance of the proposed algorithm is tested on sets of widely-used benchmark multi-objective test problems for DTLZ. The results comparing and analysis are conduced by comparing it with the state-of-art evolutionary multi-objective optimization algorithm NSGA-III to verify the effectiveness and efficiency of the proposed method.

Real-world problems are usually composed of two or more (potentially NP-Hard) problems that are interdependent on each other. Such problems have been recently identified as "multi-hard problems" and various strategies for solving them have been proposed. One of the most successful of the strategies is based on a decomposition approach, where each of the components of a multi-hard problem is solved separately (by state-of-the-art solver) and then a negotiation protocol between the sub-solutions is applied to mediate a global solution. Multi-hardness is, however, not the only crucial aspect of real-world problems. Many real-world problems operate in a dynamically-changing, uncertain environment. Special approaches such as risk analysis and minimization may be applied in cases when we know the possible variants of constraints and criteria, as well as their probabilities. On the other hand, adaptive algorithms may be used in the case of uncertainty about criteria variants or probabilities. While such approaches are not new, their application to multi-hard problems has not yet been studied systematically. In this paper we extend the benchmark problem for multi-hardness with the aspect of uncertainty. We adapt the decomposition-based approach to this new setting, and compare it against another promising heuristic (Monte-Carlo Tree Search) on a large publicly available dataset. Our comparisons show that the decomposition-based approach outperforms the other heuristic in most cases.

Learning classifier systems (LCSs) are rule-based evolutionary algorithms uniquely suited to classification and data mining in complex, multi-factorial, and heterogeneous problems. LCS rule fitness is commonly based on accuracy, but this metric alone is not ideal for assessing global rule `value' in noisy problem domains, and thus impedes effective knowledge extraction. Multi-objective fitness functions are promising but rely on knowledge of how to weigh objective importance. Prior knowledge would be unavailable in most real-world problems. The Pareto-front concept offers a strategy for multi-objective machine learning that is agnostic to objective importance. We propose a Pareto-inspired multi-objective rule fitness (PIMORF) for LCS, and combine it with a complimentary rule-compaction approach (SRC). We implemented these strategies in ExSTraCS, a successful supervised LCS and evaluated performance over an array of complex simulated noisy and clean problems (i.e. genetic and multiplexer) that each concurrently model pure interaction effects and heterogeneity. While evaluation over multiple performance metrics yielded mixed results, this work represents an important first step towards efficiently learning complex problem spaces without the advantage of prior problem knowledge. Overall the results suggest that PIMORF paired with SRC improved rule set interpretability, particularly with regard to heterogeneous patterns.

Existing methods for multi-objective optimization usually provide only an approximation of a Pareto front, and there is little theoretical guarantee of finding the real Pareto front. This paper is concerned with the possibility of fully determining the true Pareto front for those continuous multi-objective optimization problems for which there are a finite number of local optima in terms of each single objective function and there is an effective method to find all such local optima. To this end, some generalized theoretical conditions are firstly given to guarantee a complete cover of the actual Pareto front for both discrete and continuous problems. Then based on such conditions, an effective search procedure inspired by the rising sea level phenomenon is proposed particularly for continuous problems of the concerned class. Even for general continuous problems to which not all local optima are available, the new method may still work well to approximate the true Pareto front. The good practicability of the proposed method is especially underpinned by multi-optima evolutionary algorithms. The advantages of the proposed method in terms of both solution quality and computational efficiency are illustrated by the simulation results.