Internet energy consumption has increased rapidly, and energy conservation has become a significant issue that requires focused research efforts. The most promising solution is to identify the minimum power subsets within the network and shut down unnecessary network devices and links to satisfy traffic loads. Due to their distributed network control, implementing a centralized and coordinated strategy in traditional networks is challenging. Software-Defined Networking (SDN) is an emerging technology with dynamic, manageable, cost-effective, and adaptable solutions. SDN decouples network control and forwarding functions, allowing network control to be directly programmable, centralizing control with a global network view to manage power states. Nevertheless, it is crucial to develop efficient algorithms that leverage the centralized control of SDN to achieve maximum energy savings and consider peak traffic times. Traffic demand usually cannot be satisfied, even when all network devices are active. This work jointly addresses the routing of traffic flows and the assignment of SDN devices to these flows, called the Routing and Device Assignment (RDA) problem. It simultaneously seeks to minimize the network’s energy consumption and blocked traffic flows. For this approach, we develop an exact solution based on Mixed-Integer Linear Programming (MILP) as well as a metaheuristic based on a Genetic Algorithm (GA) that seeks to optimize both criteria by routing flows efficiently and suspending devices not used by the flows. Conducted simulations on traffic environment scenarios show up to 34% savings in overall energy consumption for the MILP and 33% savings achieved by the GA. These values are better than those obtained using competitive state-of-the-art strategies.

Hybrid-software-defined networks (HSDN) have opened up an enormous range of functionality and benefits for network users and administrators. Many of these functionalities have been extensively studied and addressed over the past few years. However, it is not a panacea as it brings with it many design challenges to get a robust and reliable network. In this paper, we focus on one of the SDN challenges: the incremental deployment of SDN devicesB in HSDN treated as an optimization problem. In this context, we developed a mixed integer linear programming (MILP) and a genetic algorithm (GA) considering a hybrid deployment scheme that combines current incremental deployment and replaced deployment techniques. The proposed strategy determines which traditional devices will be replaced by SDN devices, which SDN devices will be added to the network changing its topology, and how the traffic will be routed. Consequently, the aim is to minimize the deployment cost, minimize the routing cost and maximize the traffic controlled by the SDN network simultaneously. The experiments show that the proposed hybrid deployment approach is promising compared to current techniques, and the GA is more robust and scalable than the MILP as the traffic volume increases.

Software defined networking (SDN) is an emerging technology based on the separation of the control plane and the data plane. This allows to obtain benefits, in comparison with traditional networks, in terms of network management, global monitoring-control, cost reduction, and in particular the energy saving by the strategic activation of devices. In this paper, we propose an approach that seeks to minimize the global energy consumption of the network by suspending inactive devices, such as chassis and line cards, as well as limiting the use of links in traffic sessions. For this purpose, we developed an Integer Linear Programming (ILP) model for the SDN routing problem in order to obtain the minimum energy consumption, subject to satisfy all traffic demands. The experimental results on two network topologies for a set of static traffic requests indicate that the proposed model is promising, saving up to 42% of the global energy consumption obtaining a better performance to the models proposed in the literature. On the other hand, the experimental results for incremental semi-dynamic traffic indicate that the performance of the optimization with re-routing improves the approach without re-routing when increasing the traffic in the network, but this improvement is not always perceptible. The approach without re-routing in terms of scalability is promising, by increasing the traffic load not generate interruptions to the traffic already attended and affect the quality of the service.

Medical Image Registration (MIR) is a challenge that arises in many image processing applications when multiple images must be aligned. We deal with the case of multi-modalities that is approached as an optimization problem. In MIR deterministic algorithms are used mainly, the disadvantage is that many of them get trapped in local optima, especially in multi-modal registration. This work aims to overcome this disadvantage using Scatter Search and Particle Swarm as optimization algorithms, with the mutual information approach proposed by Mattes et. al. The proposed optimizers were tested and contrasted with Reference Algorithms. A multi-modal rigid 3D / 3D of brain medical image registration scheme was implemented, and it was validated in RIRE project. The qualitative and quantitative validation of the results was satisfactory; the results demonstrated the accuracy and applicability of the proposed methods in comparison to conventional methods, as well as not being trapped in local optima.

In this paper it is considered the image registration (IR) between medical images of computed tomography and magnetic resonance. Our approach formulates the IR as an optimization problem where mutual information cost function is used as a similarity metric (cost function). The Extremal Optimization algorithm is implemented as the optimizer. The numerical results are contrasted against two state of the art optimization algorithms for this kind of problems (being one deterministic and another evolutionary). Our approach is competitive with the deterministic algorithm in accuracy and with the evolutionary algorithms in computational cost. The qualitative results are quite satisfactory with a 83 % of success, whilst the quantitative results present an average error of 0.36mm with registrations of CT with proton density MR. The results show that the proposal is useful for multimodal registrations.