ECONOMIC LOAD DISPATCH BASED ON HYBRID EVOLUTIONARY ALGORITHM AND FUZZY NUMBER RANKING METHOD

2006 ◽  
Vol 14 (02) ◽  
pp. 199-209
Author(s):  
GUOLI ZHANG ◽  
GENGYIN LI ◽  
HONG XIE ◽  
JIANWEI MA
Keyword(s):  
Cost Function ◽  
Evolutionary Algorithm ◽  
Fuzzy Number ◽  
Ranking Method ◽  
Economic Load Dispatch ◽  
Hybrid Evolutionary Algorithm ◽  
Novel Method ◽  
Fuzzy Cost ◽  
The Cost ◽  
Constrained Conditions

In this paper we propose a new economic load dispatch model considered the cost function coefficients with uncertainties and the constraints of ramp rate. The uncertain parameters are represented by fuzzy numbers, with the model called fuzzy dynamic economic load dispatch model (FDELD). A novel hybrid evolutionary algorithm and fuzzy number ranking method is proposed to solve FDELD problem. Hybrid evolutionary algorithm combines evolutionary algorithm of very strong global search ability with quasi-simplex technique of better local search capability. The fuzzy number ranking method is used to compare the fuzzy cost function values when optimizing fuzzy cost function. In addition, this paper gives a novel method dealing with directly constrained conditions, and it is not necessary to construct penalty function, as a common disposal constraints method. The experimental study shows that FDELD is practical and the algorithm and techniques proposed are very efficient to solve FDELD problem.

scholarly journals The Application of an Evolutionary Algorithm to the Optimization of a Mesoscale Meteorological Model

2009 ◽  
Vol 48 (2) ◽  
pp. 317-329 ◽  
Author(s):  
Lance O’Steen ◽  
David Werth
Keyword(s):  
Cost Function ◽  
Evolutionary Algorithm ◽  
Synthetic Data ◽  
Atmospheric Model ◽  
Atmospheric Modeling ◽  
Model Parameters ◽  
Meteorological Model ◽  
Rms Error ◽  
Mesoscale Atmospheric Model ◽  
The Cost

Abstract It is shown that a simple evolutionary algorithm can optimize a set of mesoscale atmospheric model parameters with respect to agreement between the mesoscale simulation and a limited set of synthetic observations. This is illustrated using the Regional Atmospheric Modeling System (RAMS). A set of 23 RAMS parameters is optimized by minimizing a cost function based on the root-mean-square (rms) error between the RAMS simulation and synthetic data (observations derived from a separate RAMS simulation). It is found that the optimization can be done with relatively modest computer resources; therefore, operational implementation is possible. The overall number of simulations needed to obtain a specific reduction of the cost function is found to depend strongly on the procedure used to perturb the “child” parameters relative to their “parents” within the evolutionary algorithm. In addition, the choice of meteorological variables that are included in the rms error and their relative weighting are also found to be important factors in the optimization.

scholarly journals Online Reference Trajectory Adaptation: A Personalized Control Strategy for Lower Limb Exoskeletons

2021 ◽  
Author(s):  
Mohammad Shushtari ◽  
Rezvan Nasiri ◽  
Arash Arami
Keyword(s):  
Cost Function ◽  
Lower Limb ◽  
Interaction Force ◽  
Reference Trajectory ◽  
Time Symmetry ◽  
Spatiotemporal Parameters ◽  
Novel Method ◽  
The Cost ◽  
Limb Rehabilitation ◽  
Lower Limb Rehabilitation

This paper presents a novel method for reference trajectory adaptation in lower limb rehabilitation exoskeletons during walking. Our adaptation rule is extracted from a cost function that penalizes both interaction force and trajectory modification. By adding trajectory modification term into the cost function, we restrict the boundaries of the reference trajectory adaptation according to the patient's motor capacity. The performance of the proposed adaptation method is studied analytically in terms of convergence and optimality. We also developed a realistic dynamic walking simulator and utilized it in performance analysis of the presented method. The proposed trajectory adaptation technique guarantees convergence to a stable, reliable, and rhythmic reference trajectory with no prior knowledge about the human intended motion. Our simulations demonstrate the convergence of exoskeleton trajectories to those of simulated healthy subjects while the exoskeleton trajectories adapt less to the trajectories of patients with reduced motor capacity (less reliable trajectories). Furthermore, the gait stability and spatiotemporal parameters such as step time symmetry and minimum toe off clearance enhanced by the adaptation in all subjects. The presented mathematical analysis and simulation results show the applicability and effectiveness of the proposed method and its potential to be applied for trajectory adaptation in lower limb rehabilitation exoskeletons.

scholarly journals Direct Quantization for Training Highly Accurate Low Bit-width Deep Neural Networks

2020 ◽  
Author(s):  
Tuan Hoang ◽  
Thanh-Toan Do ◽  
Tam V. Nguyen ◽  
Ngai-Man Cheung
Keyword(s):  
Neural Networks ◽  
Cost Function ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Gradient Descent ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Deep Convolutional Neural Networks ◽  
Novel Method ◽  
The Cost

This paper proposes two novel techniques to train deep convolutional neural networks with low bit-width weights and activations. First, to obtain low bit-width weights, most existing methods obtain the quantized weights by performing quantization on the full-precision network weights. However, this approach would result in some mismatch: the gradient descent updates full-precision weights, but it does not update the quantized weights. To address this issue, we propose a novel method that enables direct updating of quantized weights with learnable quantization levels to minimize the cost function using gradient descent. Second, to obtain low bit-width activations, existing works consider all channels equally. However, the activation quantizers could be biased toward a few channels with high-variance. To address this issue, we propose a method to take into account the quantization errors of individual channels. With this approach, we can learn activation quantizers that minimize the quantization errors in the majority of channels. Experimental results demonstrate that our proposed method achieves state-of-the-art performance on the image classification task, using AlexNet, ResNet and MobileNetV2 architectures on CIFAR-100 and ImageNet datasets.

scholarly journals A Size-Dependent Cost Function to Solve the Inverse Elasticity Problem

2019 ◽  
Vol 9 (9) ◽  
pp. 1799
Author(s):  
Xinbo Zhao ◽  
Yanli Sun ◽  
Yue Mei
Keyword(s):  
Theoretical Analysis ◽  
Shear Modulus ◽  
Cost Function ◽  
Absolute Error ◽  
Inverse Approach ◽  
Size Dependent ◽  
L2 Norm ◽  
Novel Method ◽  
The Cost ◽  
Shear Modulus Reconstruction

Characterizing nonhomogeneous elastic property distribution of solids is of great significance in various engineering fields. In this paper, we observe that the solution to the inverse problem utilizing the standard optimization-based inverse approach is sensitive to the sizes of inclusions. The standard optimization-based inverse approach minimizes a cost function, containing the absolute error between the measured and computed displacements in L2 norm. To address this issue, we propose a novel inverse scheme to characterize nonhomogeneous shear modulus distribution of solids. In this novel method, the cost function is modified, and is dependent on the size of the inclusions. A number of simulated experiments are performed, and demonstrate that the proposed approach is capable of improving the shear modulus contrast in inclusions and reducing the size sensitivity. Furthermore, a theoretical analysis is conducted to validate what we have observed in simulated experiments. This theoretical analysis reveals that what we have observed in the simulated experiments is not induced by the numerical issues Instead, the size sensitivity issue is induced by regularization. The findings of this work encourage us to propose new cost functions for the optimization-based inverse approach to improve the quality of the shear modulus reconstruction.

A generalized fuzzy cost efficiency model

2020 ◽  
Vol 54 (6) ◽  
pp. 1775-1791
Author(s):  
Nazila Aghayi ◽  
Samira Salehpour
Keyword(s):  
Cost Efficiency ◽  
Minimum Cost ◽  
Extensive Literature ◽  
Data Envelopment ◽  
Fuzzy Environment ◽  
Decision Making Unit ◽  
Production Possibility Set ◽  
Fuzzy Cost ◽  
The Cost ◽  
Generalized Cost

The concept of cost efficiency has become tremendously popular in data envelopment analysis (DEA) as it serves to assess a decision-making unit (DMU) in terms of producing minimum-cost outputs. A large variety of precise and imprecise models have been put forward to measure cost efficiency for the DMUs which have a role in constructing the production possibility set; yet, there’s not an extensive literature on the cost efficiency (CE) measurement for sample DMUs (SDMUs). In an effort to remedy the shortcomings of current models, herein is introduced a generalized cost efficiency model that is capable of operating in a fuzzy environment-involving different types of fuzzy numbers-while preserving the Farrell’s decomposition of cost efficiency. Moreover, to the best of our knowledge, the present paper is the first to measure cost efficiency by using vectors. Ultimately, a useful example is provided to confirm the applicability of the proposed methods.

Sign in / Sign up

Export Citation Format

Share Document