Gradient Optimization Algorithm Research Articles

A short-term load demand forecasting: Levenberg–Marquardt (LM), Bayesian regularization (BR), and scaled conjugate gradient (SCG) optimization algorithm analysis

A short-term load demand forecasting: Levenberg–Marquardt (LM), Bayesian regularization (BR), and scaled conjugate gradient (SCG) optimization algorithm analysis

Dual Attention Adversarial Attacks With Limited Perturbations.

The construction of undetectable adversarial examples with few perturbances remains a difficult problem in adversarial attacks. At present, most solutions use the standard gradient optimization algorithm to build adversarial examples by applying global perturbations to benign samples and then launch attacks on the targets (e.g., face recognition systems). However, when the perturbance size is limited, the performance of these approaches suffers substantially. The content of crucial places in an image, on the other hand, will impact the final prediction; if these areas can be investigated and limited perturbances introduced, an acceptable adversarial example will be constructed. Based on the foregoing research, this article offers a dual attention adversarial network (DAAN) to produce adversarial examples with limited perturbations. DAAN initially searches for effective areas in an input image using the spatial attention network and channel attention network, and then creates space and channel weights. Following that, these weights direct an encoder and a decoder to generate effective perturbation, which is then combined with the input to produce an adversarial example. Finally, the discriminator determines if the created adversarial examples are true or false, and the attacked model is utilized to determine whether the generated samples fit the attack targets. Extensive studies on various datasets show that DAAN not only delivers the best attack performance across all comparison algorithms with few perturbations, but it can also significantly improve the defensiveness of the attacked models.

Structural graph federated learning: Exploiting high-dimensional information of statistical heterogeneity

With the recent progress in graph-federated learning (GFL), it has demonstrated a promising performance in effectively addressing challenges associated with heterogeneous clients. Although the majority of advances in GFL have been focused on techniques for elucidating the intricate relationships among clients, existing GFL methods have two limitations. First, current methods comprising the use of low-dimensional graphs fail to accurately depict the associations between clients, thereby compromising the performance of GFL. Second, these methods may disclose additional information when sharing client-side hidden representations. This paper presents a structural GFL (SGFL) framework and a suite of novel optimization methods. SGFL addresses the limitations of existing GFL approaches with three original contributions. Firstly, our approach advocates the dynamic construction of federated learning (FL) graphs by leveraging the high-dimensional information inherent among clients, while enabling the discovery of hierarchical communities within clients. Secondly, we present SG-FedX, a novel federated stochastic gradient optimization algorithm that mitigates the effects of heterogeneity by intelligently using a global representation. Furthermore, SG-FedX introduces a strict sharing mechanism that protects client privacy more effectively by refraining from sharing client information beyond the model parameters. Our comparative evaluations, conducted against ten representative FL algorithms under challenging non-independently-and-identically-distributed settings, demonstrated the superior performance of SG-FedX. It was noted that, in the cross-dataset scenarios, SG-FedX outperformed the second-best baseline by 8.12% and 7.91% in personalization and generalization performance, respectively.

Research on priority scheduling strategy for smoothing power fluctuations of microgrid tie‐lines based on PER‐DDPG algorithm

AbstractThe variability of renewable energy within microgrids (MGs) necessitates the smoothing of power fluctuations through the effective scheduling of internal power equipment. Otherwise, significant power variations on the tie‐line connecting the MG to the main power grid could occur. This study introduces an innovative scheduling strategy that utilizes a data‐driven approach, employing a deep reinforcement learning algorithm to achieve this smoothing effect. The strategy prioritizes the scheduling of MG's internal power devices, taking into account the stochastic charging patterns of electric vehicles. The scheduling optimization model is initially described as a Markov decision process with the goal of minimizing power fluctuations on the interconnection lines and operational costs of the MG. Subsequently, after preprocessing the historical operational data of the MG, an enhanced scheduling strategy is developed through a neural network learning process. Finally, the results from four scheduling scenarios demonstrate the significant impact of the proposed strategy. Comparisons of reward curves before and after data preprocessing underscore its importance. In contrast to optimization results from deep deterministic policy gradient, soft actor‐critic, and particle swarm optimization algorithms, the superiority of the deep deterministic policy gradient algorithm with the addition of a priority experience replay mechanism is highlighted.

On the impact of B0 shimming algorithms on single-voxel MR spectroscopy.

To assess the impact of different B0 shimming algorithms on MRS. B0 field maps and single-voxel MR spectroscopy were acquired in the prefrontal cortex of five volunteers at 3 T using five different B0 shimming approaches. B0 shimming was achieved using Siemens' proprietary shim algorithm, in addition to the Pseudo-Inverse (PI), Quadratic Programming (QuadProg), Least Squares (LSq), and Gradient optimization (Grad) algorithms. The standard deviation of the shimmed B0 field, as well as the SNR and FWHM of the measured metabolites, was used to evaluate the performance of each B0 shimming algorithm. Compared to Siemens's shim, significant reductions (p < 0.01) in the standard deviation of the B0 field distribution within the MRS voxel were observed for the PI, QuadProg, and Grad algorithms (3.8 Hz, 7.3 Hz, and 3.9 Hz respectively, compared to 11.5 Hz for Siemens), but not for the LSq (12.9 Hz) algorithm. Moreover, significantly increased SNR and reduced FWHM for the N-acetylaspartate metabolite were consistent with the improvement in B0 homogeneity for the aforementioned shimming algorithms. Here, we demonstrate that the choice of B0 shimming algorithm can have a significant impact on the quality of MR spectra and that significant improvements in spectrum quality could be achieved by using alternatives to the default vendor approach.

Optimal bidding strategy for the price-maker virtual power plant in the day-ahead market based on multi-agent twin delayed deep deterministic policy gradient algorithm

In recent years, distributed energy resources (DERs) have developed greatly, and the total capacity of resources aggregated by virtual power plants (VPPs) has increased. The role VPP plays in the market is changing. It is necessary to explore VPP's bidding strategy in the electricity market based on the impact of VPP on the clearing price. At the same time, the strategy game of different market players will also impact VPP's strategy. The multi-agent twin delayed deep deterministic policy gradient (MATD3) algorithm is used to solve the problem of price-maker VPP participation in the day-ahead (DA) market. VPP is required to submit the power and prices of electricity in multi-segments at different times. In the market bidding process, the main market participants are considered as agents. Iterative refinement of each player's strategy is achieved through multi-agent reinforcement learning, with the primary aim of maximizing revenue. For the VPP, the MATD3 algorithm improved the reward by approximately 65 % and increased the convergence speed by 17 % compared to the multi-agent deep deterministic policy gradient and multi-agent proximal policy optimization algorithms. The effects of different influences on VPP's bidding strategy are analyzed, which can provide a decision-making reference for market participants.

Accelerated optimization through time-scale analysis of inertial dynamics with asymptotic vanishing and Hessian-driven dampings

ABSTRACT Gradient optimization algorithms can be effectively studied from the perspective of ordinary differential equations (ODEs), where these algorithms are obtained through the temporal discretization of the continuous dynamics. This approach provides a powerful tool to comprehend acceleration phenomena in optimization, thanks to time-scale techniques and Lyapunov analysis. In the context of a Hilbert setting, our study focuses on the rapid optimization properties of inertial dynamics, which combine asymptotically vanishing viscous damping with Hessian-driven damping. These dynamics are derived as high-resolution ODEs from both the Nesterov accelerated gradient method and the Ravine method. For a general differentiable convex function f, choosing the viscous damping coefficient in the form of α / t with 3 $ ]]> α > 3 guarantees an inverse quadratic convergence rate of the values, i.e. o ( 1 / t 2 ) , the weak convergence of trajectories towards optimal solutions, and the fast convergence of gradients towards zero. By carefully scaling the dynamics temporally and based on the tuning of the damping coefficient in front of the Hessian term, we identify the limit dynamic as α becomes large. In particular, we examine the case where the limit dynamic corresponds to the Levenberg-Marquardt regularization of Newton's continuous method. This explanation accounts for the aforementioned fast convergence properties and provides fresh insights into the complexity of these methods, which play a central role in optimization for high-dimensional problems. The interplay between numerical algorithms and continuous-time ODEs plays a fundamental role in our analysis for the design and understanding of accelerated optimization algorithms. Numerical experiments are presented to illustrate and support the theoretical results.

A High-Speed Acoustic Echo Canceller Based on Grey Wolf Optimization and Particle Swarm Optimization Algorithms.

Currently, the use of acoustic echo cancellers (AECs) plays a crucial role in IoT applications, such as voice control appliances, hands-free telephony and intelligent voice control devices, among others. Therefore, these IoT devices are mostly controlled by voice commands. However, the performance of these devices is significantly affected by echo noise in real acoustic environments. Despite good results being achieved in terms of echo noise reductions using conventional adaptive filtering based on gradient optimization algorithms, recently, the use of bio-inspired algorithms has attracted significant attention in the science community, since these algorithms exhibit a faster convergence rate when compared with gradient optimization algorithms. To date, several authors have tried to develop high-performance AEC systems to offer high-quality and realistic sound. In this work, we present a new AEC system based on the grey wolf optimization (GWO) and particle swarm optimization (PSO) algorithms to guarantee a higher convergence speed compared with previously reported solutions. This improvement potentially allows for high tracking capabilities. This aspect has special relevance in real acoustic environments since it indicates the rate at which noise is reduced.

Ensemble Random Forest-based Gradient Optimization based Energy Efficient Video Processing System for Smart Traffic Surveillance System

Deep learning solutions in big data applications can benefit cloud centres and can also lead to network communication overhead. Typically, data collected from traffic are sent to the traffic management centre for analysis. However, this process can worsen the network route to the traffic management centre. A two-tier mechanism has been developed to address this issue, which performs vehicle speed estimation and traffic congestion detection for efficient traffic management. The real-time traffic video data are captured and the video frames are initially processed through a foreground extraction process, which extracts the temporarily stopped vehicles on the road by removing background pixels from the frames. The video frames are then wrapped in an up-down view to remove the influence of the observation angle. The traffic congestion is then detected accurately based on the traffic characteristics using the proposed Ensemble Random Forest-based Gradient Optimization (ERF-GO) algorithm. The generalization error occurs when learning complex features on frames is minimized using a gradient-based optimization (GO) algorithm. Finally, the learned information on traffic conditions is forwarded to the cloud and edge computing environments based on network connection speed. The efficiency of the proposed ERF-GO is investigated in terms of performance metrics, namely root mean square error, speed detection error, execution time, computational cost, accuracy, latency, workload balance, precision, recall, f-measure, and congestion detection error rate. The analytic result displays that the proposed ERF-GO algorithm attains a greater accuracy rate of about 98.65% in detecting traffic congestion which is comparably higher than state-of-the-art methods.

An optimal solutions-guided deep reinforcement learning approach for online energy storage control

As renewable energy becomes more prevalent in the power grid, energy storage systems (ESSs) are playing an ever-increasingly crucial role in mitigating short-term supply–demand imbalances. However, the operation and control of ESS are not straightforward, given the ever-changing electricity prices in the market environment and the stochastic and intermittent nature of renewable energy generations, which respond to real-time load variations. In this paper, we propose a deep reinforcement learning (DRL) approach to address the electricity arbitrage problem associated with optimal ESS management. First, we analyze the structure of the optimal offline ESS control problem using the mixed-integer linear programming (MILP) formulation. This formulation identifies optimal control actions to absorb excess renewable energy and perform price arbitrage strategies. To tackle the uncertainties inherent in the prediction data, we then recast the online ESS control problem into a Markov Decision Process (MDP) framework and develop the DRL approach, which involves integrating the optimal offline control solution obtained from the training data into the training process and introducing noise to the state transitions. Unlike typical offline DRL training over a long time interval, we employ the Deep Deterministic Policy Gradient (DDPG) and Proximal Policy Optimization (PPO) algorithms with smaller neural networks training over a short time interval. Numerical studies demonstrate the promising potential of the proposed DRL-enabled approach for achieving better online control performance than the model predictive control (MPC) method under different price errors. This highlights the sample efficiency and robustness of our DRL approaches in managing ESS for electricity arbitrage.

A level set reliability-based topology optimization (LS-RBTO) method considering sensitivity mapping and multi-source interval uncertainties

With the diversification of engineering structure performance requirements and the continuous development of structural design refinement, structural design methods are facing more and more factors to be considered. It is necessary to develop advanced design technology. In this paper, a sensitivity mapping technique is proposed to improve the effect of topology optimization based on a gradient optimization algorithm. The applicability of this technology is analyzed. In addition, considering the influence of multi-source uncertainties in the whole life cycle of the structure, a reliability-based topology optimization strategy based on the level set method is proposed. The sensitivity of displacement constraint and reliability constraint with pseudo time is derived. Numerical examples and Monte Carlo verification results fully illustrate the applicability, effectiveness, and efficiency of the proposed method. This method has been successfully applied to the topology optimization design of the rocket skid structure.

Teaching Chinese Painting Colour Based on Intelligent Image Processing Technology

Abstract This paper constructs a Chinese painting color teaching platform based on intelligent image color processing technology. Firstly, the region segmentation method is used to reasonably segment the pixel points according to the similar values of color and texture parameters of the image. Then, the image’s primary color grayscale parameters are fuzzy, detected, equalized, and fused by color difference values. Finally, the gradient optimization algorithm is combined to identify and control the image color parameters. The results show that the highest value of peak signal-to-noise ratio can reach 73.4db for the images processed by the method of this paper, and the mean value of STRESS is kept between 0-10%. The intelligent image color processing technique has been proven to enhance the aesthetics and innovation of Chinese painting colors in students.

Intelligent Traffic Data Transmission and Sharing Based on Optimal Gradient Adaptive Optimization Algorithm

This work aims to improve the transmission and sharing efficiency of intelligent transportation data and promote the further development of intelligent transportation and smart city. In this work, an EEMR (Energy Efficient Multi-hop Routing) is designed for the intelligent transportation wireless sensor network. In the EEMR algorithm, the base station runs the IAP clustering algorithm for network clustering after receiving the information of all surviving nodes. A method called ACRR (Adaptive Cluster-head Round Robin) is proposed for local dynamic election of cluster heads. In addition, the deep learning-based stochastic gradient descent algorithm and its evolution algorithm are sorted out, and its application in practical scenarios is analyzed. Due to the disadvantages of the adaptive algorithm in the current data processing process, the gradient optimization algorithm based on deep learning is adopted and the concept of adaptive friction coefficient is applied to the Adam algorithm to obtain a new adaptive algorithm (TAdam). The simulation experiment reveals that the proportion of network surviving nodes of the EEMR algorithm is still as high as 90% in 1,500 rounds of data collection. This shows that the EEMR algorithm achieves the energy balance of the network nodes as much as possible while minimizing the system energy consumption. In application scenario 1, when the network surviving nodes of the four data collection algorithms compares dropped below 40%, the number of surviving nodes in the EEMR algorithm is still as high as 97.6%. On the PTB (Penn Tree Bank) test data set, the TAdam algorithm shows the fastest convergence speed and the best generalization performance. The TAdam algorithm based on deep learning discussed in this work was of great significance for improving the transmission and sharing efficiency of intelligent transportation data.

An explicit structural optimization method for temperature-sensitive hydrogel actuation devices

Hydrogel actuation devices are commonly composed of responsive and passive materials, and their actuation effect depends on their unique structure. In this paper, an explicit optimization method is proposed for the design of temperature-sensitive hydrogel-based soft devices involving swelling and shrinking to achieve specific actuation effects. In this method, the outline of configuration and the responsive layer are explicitly described by the ordered B-spline curve and movable hydrogel patch, respectively. The parametric modeling method is proposed to construct the geometric model with local features, which can transform the complex patch stacking problem into the fusion problem of three-dimensional geometry. Based on the large deformation theory of temperature-sensitive hydrogel, the deformation behavior of soft device is accurately simulated. The adaptive mesh division method is applied to numerical simulation of complex structures to avoid mesh distortion. Furthermore, the optimization problem is effectively solved by combining the gradient optimization algorithm. Several numerical examples are presented to verify the accuracy of the method, and interesting structures such as the Miura-ori structure, switch and bionic structures are designed. The method can significantly reduce the optimization design variables, and the explicit optimization results can be used as the basis for the additive manufacturing of soft devices.

Comparison of Different Parameters of Feedforward Backpropagation Neural Networks in DEM Height Estimation for Different Terrain Types and Point Distributions

Digital Elevation Models (DEMs) are commonly used for environment, engineering, and architecture-related studies. One of the most important factors for the accuracy of DEM generation is the process of spatial interpolation, which is used for estimating the height values of the grid cells. The use of machine learning methods, such as artificial neural networks for spatial interpolation, contributes to spatial interpolation with more accuracy. In this study, the performances of FBNN interpolation based on different parameters such as the number of hidden layers and neurons, epoch number, processing time, and training functions (gradient optimization algorithms) were compared, and the differences were evaluated statistically using an analysis of variance (ANOVA) test. This research offers significant insights into the optimization of neural network gradients, with a particular focus on spatial interpolation. The accuracy of the Levenberg–Marquardt training function was the best, whereas the most significantly different training functions, gradient descent backpropagation and gradient descent with momentum and adaptive learning rule backpropagation, were the worst. Thus, this study contributes to the investigation of parameter selection of ANN for spatial interpolation in DEM height estimation for different terrain types and point distributions.

Deep-Reinforcement-Learning-Based IRS for Cooperative Jamming Networks Under Edge Computing

Effective energy design and secure communications are critical in the Internet of Things (IoT). A cooperative jamming (CJ) scheme based on deep reinforcement learning (DRL) is proposed for intelligent reflecting surface (IRS) aided secure cooperative network with eavesdroppers. Our goal is to maximize the average secrecy rate, or energy efficiency with secrecy constraints by jointly optimising the transmit, jamming beamforming matrices and IRS phase-shift matrix. In order to figure out the challenging non-convex optimization problem, the deep deterministic policy gradient (DDPG) optimization algorithm is proposed to solve the energy efficiency maximization problem. In order to speed up task processing and reduce service delay, the edge computing server is employed for DRL training to improve computing speed and promote secure communication efficiency. By taking advantages of the features of proximity to end devices and computing resources, the edge devices provide a low latency efficient training support to the legal users and real-time control to the IRS units. By this way, a high security and low energy consumption IoT system is built. Numerical results show that the novel scheme improves the secrecy rate and energy efficiency compared with the benchmark scheme.

Analysis of the application methods of film and television media and images in the era of big data cloud

Abstract In order to give full play to the application of big data in film and television media and imaging in the cloud era, this study proposes a communication-efficient distributed deep neural network training method based on the DANE algorithm framework. The DANE algorithm is an approximate Newtonian method that has been widely used in communication-efficient distributed machine learning. It has the advantages of fast convergence and no need to calculate the inverse of the Hessian matrix, which can significantly reduce the communication and computational overhead in high-dimensional situations. In order to further improve the computational efficiency, it is necessary to study how to speed up the local optimization of DANE. It is a feasible method to choose to use the most popular adaptive gradient optimization algorithm Adam to replace the commonly used stochastic gradient descent method to solve the local single-machine suboptimization problem of DANE. Experiments show that Adam-based optimization can converge significantly faster than the original SGD-based implementation with little sacrifice in model generalization performance. With the increase of sampling rate, DANE-Adam significantly outperforms the DANE method in terms of convergence speed, and at the same time, the accuracy can be kept almost unchanged, which are 0.96, 0.88 and 0.75, respectively. This shows that Adam-based optimization can converge significantly faster than the original SGD-based implementation with little sacrifice in model generalization performance, with significant potential value.

Fixed-Time Optimization of Perturbed Multi-Agent Systems under the Resource Constraints

In this paper, a novel fixed-time distributed optimization algorithm is proposed to solve the multi-agent collaborative optimization (MSCO) problem with local inequality constraints, global equation constraints and unknown disturbances. At first, a penalty function method is used to eliminate the local inequality constraints and transform the original problem into a problem without local constraints. Then, a novel three-stage control scheme is designed to achieve a robust fixed-time convergence. In the first stage, a fixed-time reaching law is given to completely eliminate the effect of unknown disturbances with the aid of the integral sliding mode control method; in the second stage, a suitable interaction strategy is provided such that the whole system could satisfy the global constraints in fixed-time; in the third stage, a fixed-time gradient optimization algorithm of the multi-agent system is presented, with which the states of all the agents will converge to the minimum value of the global objective in a fixed-time. Finally, the effectiveness of the proposed control strategy is verified in the problem of wind farm co-generation with 60 wind turbines.

NSGA-PINN: A Multi-Objective Optimization Method for Physics-Informed Neural Network Training

This paper presents NSGA-PINN, a multi-objective optimization framework for the effective training of physics-informed neural networks (PINNs). The proposed framework uses the non-dominated sorting genetic algorithm (NSGA-II) to enable traditional stochastic gradient optimization algorithms (e.g., ADAM) to escape local minima effectively. Additionally, the NSGA-II algorithm enables satisfying the initial and boundary conditions encoded into the loss function during physics-informed training precisely. We demonstrate the effectiveness of our framework by applying NSGA-PINN to several ordinary and partial differential equation problems. In particular, we show that the proposed framework can handle challenging inverse problems with noisy data.

Solar-Thermal-Chemical Integrated Design of a Cavity-Type Solar-Driven Methane Dry Reforming Reactor

In this work, the solar-thermal-chemical integrated design for a methane dry reforming reactor with cavity-type solar absorption was numerically performed. Combined with a multiphysical reactor model, the gradient optimization algorithm was used to find optimal radiation flux distribution with fixed total incident solar energy for maximizing overall hydrogen yield, defined as the ratio of molar flow of exported hydrogen to imported methane, which can be applied for guiding the optical property design of solar adsorption surface. The comprehensive performances of the reactor under the conditions of original solar flux and optimal solar flux were analyzed and compared. The results show that for the inlet volume flow rate of 8–14 L·min−1, the hydrogen production rate was increased by up to 5.10%, the energy storage efficiency was increased by up to 5.55%, and the methane conversion rate was increased by up to 6.01%. Finally, the local absorptivities of the solar-absorptive coating on the cavity walls were optimized and determined using a genetic algorithm, which could realize the predicted optimal radiation flux distribution.