Time filter

Source Type

Iacca G.,3 Innovation Center for Advanced Sensors and Sensor Systems
2012 12th UK Workshop on Computational Intelligence, UKCI 2012

Driven by a broad range of applications, the Computational Intelligence research community has recently put a growing interest on the emergent technology of Wireless Sensor Networks (WSNs). Due to their distributed structure, WSNs pose several technical challenges caused by local failures, network issues and severely constrained hardware resources. Nevertheless, the possibility to perform an online optimization within WSNs is appealing since it might lead the path to advanced network features like intelligent sensing, distributed modelling, self-optimizing protocols, anomaly detection, etc. just to name a few. In this paper we present DOWSN, a novel Distributed Optimization framework for WSNs. Based on an island model, DOWSN is characterized by a peer-to-peer infrastructure in which each node executes an optimization process and shares pieces of information, i.e. local achievements, with its neighbors. Preliminary experiments show that DOWSN is able to efficiently exploit the communication capabilities and the inherently parallel nature of WSNs, thus finding optimal solutions fast and reliably. © 2012 IEEE. Source

Neri F.,De Montfort University | Neri F.,University of Jyvaskyla | Mininno E.,University of Jyvaskyla | Iacca G.,3 Innovation Center for Advanced Sensors and Sensor Systems
Information Sciences

Some real-world optimization problems are plagued by a limited hardware availability. This situation can occur, for example, when the optimization must be performed on a device whose hardware is limited due to cost and space limitations. This paper addresses this class of optimization problems and proposes a novel algorithm, namely compact Particle Swarm Optimization (cPSO). The proposed algorithm employs the search logic typical of Particle Swarm Optimization (PSO) algorithms, but unlike classical PSO algorithms, does not use a swarm of particles and does not store neither the positions nor the velocities. On the contrary, cPSO employs a probabilistic representation of the swarm's behaviour. This representation allows a modest memory usage for the entire algorithmic functioning, the amount of memory used is the same as what is needed for storing five solutions. A novel interpretation of compact optimization is also given in this paper. Numerical results show that cPSO appears to outperform other modern algorithms of the same category (i.e. which attempt to solve the optimization despite a modest memory usage). In addition, cPSO displays a very good performance with respect to its population-based version and a respectable performance also with respect to some more complex population-based algorithms. A real world application in the field of power engineering and energy generation is given. The presented case study shows how, on a model of an actual power plant, an advanced control system can be online and real-time optimized. In this application example the calculations are embedded directly on the real-time control system. © 2013 Elsevier Inc. All rights reserved. Source

Iacca G.,3 Innovation Center for Advanced Sensors and Sensor Systems | Caraffini F.,De Montfort University | Caraffini F.,University of Jyvaskyla | Neri F.,De Montfort University | And 2 more authors.
2013 IEEE Congress on Evolutionary Computation, CEC 2013

This paper introduces two lightweight variants of ISPO, a Single Particle Optimization algorithm recently proposed in the literature. The goal of this work is to improve upon the performance of the original ISPO, still bearing in mind its admirable algorithmic simplicity. The first variant, namely ISPO-restart, combines in a memetic fashion the logics of ISPO with a partial restart mechanism similar to the binomial crossover typically used in Differential Evolution. The second variant, named VISPO, builds on top of the restart process a very simple learning stage which tries to adapt the algorithm behaviour to the (non)-separability of the problem. Numerical results obtained on three complete optimization benchmarks show that not only the two algorithms are able to improve, incrementally, upon the performance of ISPO, but also they show respectable performance in comparison with modern complex state-of-the-art methods, especially when the problem dimensionality increases. © 2013 IEEE. Source

Iacca G.,3 Innovation Center for Advanced Sensors and Sensor Systems | Caraffini F.,De Montfort University | Neri F.,De Montfort University
International Journal of Neural Systems

We propose Multi-Strategy Coevolving Aging Particles (MS-CAP), a novel population-based algorithm for black-box optimization. In a memetic fashion, MS-CAP combines two components with complementary algorithm logics. In the first stage, each particle is perturbed independently along each dimension with a progressively shrinking (decaying) radius, and attracted towards the current best solution with an increasing force. In the second phase, the particles are mutated and recombined according to a multi-strategy approach in the fashion of the ensemble of mutation strategies in Differential Evolution. The proposed algorithm is tested, at different dimensionalities, on two complete black-box optimization benchmarks proposed at the Congress on Evolutionary Computation 2010 and 2013. To demonstrate the applicability of the approach, we also test MS-CAP to train a Feedforward Neural Network modeling the kinematics of an 8-link robot manipulator. The numerical results show that MS-CAP, for the setting considered in this study, tends to outperform the state-of-the-art optimization algorithms on a large set of problems, thus resulting in a robust and versatile optimizer. © 2014 World Scientific Publishing Company. Source

Iacca G.,3 Innovation Center for Advanced Sensors and Sensor Systems | Caraffini F.,De Montfort University | Caraffini F.,University of Jyvaskyla | Neri F.,De Montfort University | Neri F.,University of Jyvaskyla
Applied Soft Computing Journal

In this paper, a recently proposed single-solution memetic computing optimization method, namely three stage optimization memetic exploration (3SOME), is used to implement a self-tuning PID controller on board of a mobile robot. More specifically, the optimal PID parameters minimizing a measure of the following error on a path-following operation are found, in real-time, during the execution of the control loop. The proposed approach separates the control and the optimization tasks, and uses simple operating system primitives to share data. The system is able to react to modifications of the trajectory, thus endowing the robot with intelligent learning and self-configuration capabilities. A popular commercial robotic tool, i.e. the Lego Mindstorms robot, has been used for testing and implementing this system. Tests have been performed both in simulations and in a real Lego robot. Experimental results show that, compared to other online optimization techniques and to empiric PID tuning procedures, 3SOME guarantees a robust and efficient control behaviour, thus representing a valid alternative for self-tuning control systems. © 2012 Elsevier B.V. All rights reserved. Source

Discover hidden collaborations