The impressive evolution of the Internet of Things and the great amount of data flowing through the systems provide us with an inspiring scenario for Big Data analytics and advantageous real-time context-aware predictions and smart decision-making. However, this requires a scalable system for constant streaming processing, also provided with the ability of decision-making and action taking based on the performed predictions. This paper aims at proposing a scalable architecture to provide real-time context-aware actions based on predictive streaming processing of data as an evolution of a previously provided event-driven service-oriented architecture which already permitted the context-aware detection and notification of relevant data. For this purpose, we have defined and implemented a microservice-based architecture which provides real-time context-aware actions based on predictive streaming processing of data. As a result, our architecture has been enhanced twofold: on the one hand, the architecture has been supplied with reliable predictions through the use of predictive analytics and complex event processing techniques, which permit the notification of relevant context-aware information ahead of time. On the other, it has been refactored towards a microservice architecture pattern, highly improving its maintenance and evolution. The architecture performance has been evaluated with an air quality case study.

This paper presents a new way of measuring complexity in variable-size-chromosome-based evolutionary algorithms. Dealing with complexity is particularly useful when considering bloat in Genetic Programming. Instead of analyzing size growth, we focus on the time required for individuals' fitness evaluations, which correlates with size. This way, we consider time and space as two sides of a single coin when devising a more natural method for fighting bloat. We thus view the problem from a perspective that departs from traditional methods applied in Genetic Programming. We have analyzed first the behavior of individuals across generations, taking into account their fitness evaluation times, thus providing clues about the general practice of the evolutionary process when modern parallel and distributed computers are used to run the algorithm. This new perspective allows us to understand that new methods for bloat control can be derived. Moreover, we develop from this framework a first proposal to show the usefulness of the idea: to group individuals in classes according to computing time required for evaluation, automatically accomplished by parallel and distributed systems without any change in the underlying algorithm, when they are only allowed to breed within their classes. Experimental data confirms the strength of the approach: using computing time as a measure of individuals' complexity allows control of the natural size growth of genetic programming individuals while preserving the quality of solutions in both the parallel and sequential versions of the algorithm. INDEX TERMS Bloat, computing time, genetic programming.

In recent years, the energy-awareness has become one of the most interesting areas in our environmentally conscious society. Algorithm designers have been part of this, particularly when dealing with networked devices and, mainly, when handheld ones are involved. Although studies in this area has increased, not many of them have focused on Evolutionary Algorithms. To the best of our knowledge, few attempts have been performed before for modeling their energy consumption considering different execution devices. In this work, we propose a fuzzy rulebased system to predict energy comsumption of a kind of Evolutionary Algorithm, Genetic Prohramming, given the device in wich it will be executed, its main parameters, and a measurement of the difficulty of the problem addressed. Experimental results performed show that the proposed model can predict energy consumption with very low error values.

No abstract