Conference Paper

Power management by brain emotional learning algorithm

Univ. of Tehran, Tehran
DOI: 10.1109/ICASIC.2007.4415571 Conference: ASIC, 2007. ASICON '07. 7th International Conference on
Source: IEEE Xplore


Nowadays having the most energy efficiency is desirable in its own right from both economical and environmental points of view. Dynamic power management is a system level solution for reducing the consumed energy with putting off unused parts of the system and putting them on in an efficient time. The Emotional Learning Algorithm has been introduced to show the effect of emotions as well known stimuli in the quick and almost satisfying decision making in human. The remarkable properties of emotional learning, low computational complexity and fast training, and its simplicity in multi objective problems has made it a powerful methodology in real time control and decision systems, where the gradient based methods and evolutionary algorithms are hard to be used due to their high computational complexity. Recently the emotional approach has been successfully used to obtain multiple objectives in prediction problems of real world phenomena. At first we introduce methods of dynamic power management and then a new method based on BELBIC would be explained. The simulation results show that this method has a high efficiency in various systems.

6 Reads
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In mammalians, brain Limbic System is responsible for emotionalprocess. An important part of motor learning as well as attention isformed by the system. Brain Emotional Learning (BEL) process ofmammalians has been mathematically modeled. Based on the model,a controller architecture called Brain Emotional Learning BasedIntelligent Controller (BELBIC) has been developed. EmotionalLearning is a powerful methodology in real time control anddecision systems due to low computational complexity and fasttraining where the gradient based methods and evolutionaryalgorithms are hard to be applied because of their highcomputational complexity. In this paper, the emotional processesand the Limbic System will be reviewed. In addition, the utilizationof BELBIC model in variety of applications of control system will beexamined. The results of simulations demonstrate control systemsbased on BELBIC have good performances.
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, a brain emotional learning based intelligent controller (BELBIC) is developed to control the switched reluctance motor (SRM) speed. Like other intelligent controllers, BELBIC is model free and is suitable to control nonlinear systems. Motor parameter changes, operating point changes, measurement noise, open circuit fault in one phase and asymmetric phases in SRM are also simulated to show the robustness and superior performance of BELBIC. To compare the BELBIC performance with other intelligent controllers, Fuzzy Logic Controller (FLC) is developed. System responses with BELBIC and FLC are compared. Furthermore, by eliminating the position sensor, a method is introduced to estimate the rotor position. This method is based on Adaptive Neuro Fuzzy Inference System (ANFIS). The estimator inputs are four phase flux linkages. Suggested rotor position estimator is simulated in different conditions. Simulation results confirm the accurate rotor position estimation in different loads and speeds.
    Energy Conversion and Management 01/2011; 52(1-52):85-96. DOI:10.1016/j.enconman.2010.06.046 · 4.38 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper we propose the supervised version of neuro-based computational model of brain emotional learning (BEL). In mammalian brain, the limbic system processes emotional stimulus and consists of following two main components: amygdala and orbitofrontal cortex (OFC). Recently several models of BEL based on monotonic reinforcement learning in amygdala are proposed by researchers. Here, we introduce supervised version of BEL which can be learned by pattern-target examples. According to the experimental studies, where various comparisons are made between the proposed method, multilayer perceptron (MLP) and adaptive neuro-fuzzy inference system (ANFIS), the main feature of the presented method is fast training in prediction problems.
    Neural Networks (IJCNN), The 2012 International Joint Conference on; 06/2012
Show more