Optimization Algorithm Research Articles

Learning Force Field Parameters from Differentiable Particle-Field Molecular Dynamics.

We develop ∂-HylleraasMD (∂-HyMD), a fully end-to-end differentiable molecular dynamics software based on the Hamiltonian hybrid particle-field formalism, and use it to establish a protocol for automated optimization of force field parameters. ∂-HyMD is templated on the recently released HylleraaasMD software, while using the JAX autodiff framework as the main engine for the differentiable dynamics. ∂-HyMD exploits an embarrassingly parallel optimization algorithm by spawning independent simulations, whose trajectories are simultaneously processed by reverse mode automatic differentiation to calculate the gradient of the loss function, which is in turn used for iterative optimization of the force-field parameters. We show that parallel organization facilitates the convergence of the minimization procedure, avoiding the known memory and numerical stability issues of differentiable molecular dynamics approaches. We showcase the effectiveness of our implementation by producing a library of force field parameters for standard phospholipids, with either zwitterionic or anionic heads and with saturated or unsaturated tails. Compared to the all-atom reference, the force field obtained by ∂-HyMD yields better density profiles than the parameters derived from previously utilized gradient-free optimization procedures. Moreover, ∂-HyMD models can predict with good accuracy properties not included in the learning objective, such as lateral pressure profiles, and are transferable to other systems, including triglycerides.

Application of QPSO-BPSO in fault self-healing of distributed power distribution networks

With the widespread application of distributed power sources in distribution networks, fault self-healing technology has become the key to ensuring the reliability of power systems. The micro-grid ensures system stability with a three-layer structure, where the designed method handles optimization problems, achieving faster global search and optimal solutions. Agents develop targeted recovery strategies by understanding network load, which are then executed by higher-level agents to ensure that the optimal recovery command is implemented by the system. According to the research results, during peak load, the system successfully outputted 7 kilowatts and met the load demand through battery discharge, demonstrating its self-healing ability. The output analysis of photovoltaic and wind turbines showed that the system reasonably scheduled within 24 h according to the changes in solar energy and wind power. Based on the quantum behavior particle swarm optimization algorithm, the system has achieved lower active power loss and greater power supply capacity. Although the number of switch operations has increased, the system performance has significantly improved, meeting the requirements for improving system economy and safety. It has promoting effects on the sustainable development of future power systems.

Inversion Study on Landslide Seepage Field Based on Swarm Intelligence Optimization Least-Square Support Vector Machine Algorithm

The permeability coefficient of landslide mass, a key parameter in the study of reservoir landslides, is commonly obtained through in situ and laboratory tests; however, the tests are costly and subject to high variability, leading to potential biases. In this paper, a new method was proposed to inversely estimate the permeability coefficient of landslide layers using monitoring data of groundwater level (GWL). First, the landslide transient seepage simulation was conducted to generate sample data for permeability coefficients and GWL during a reservoir operation cycle. Second, using GWL data as input and permeability coefficient data as output, the least-square support vector machine (LSSVM) was trained with two optimization algorithms, the particle swarm optimization (PSO) algorithm and the whale optimization algorithm (WOA), to construct the nonlinear mapping relationship between simulated GWL and permeability coefficients. Third, the accurate permeability coefficients for landslide seepage simulation were inverted or predicted based on the monitored GWL. Finally, using the inverted permeability coefficients for landslide seepage simulation, we compared simulation results with actual monitored GWL and achieved good consistency. In addition, this paper compared the inversion effects of three different algorithms: the standard LSSVM, PSO-LSSVM, and WOA-LSSVM. This study showed that these three algorithms had good nonlinear fitting effects in studying landslide seepage fields. Among them, using the inversion values from PSO-LSSVM for landslide seepage simulation resulted in the smallest relative error compared to actual monitoring data. Within a single reservoir operation cycle, the simulated water level changes were also largely consistent with the monitored water level changes. The results could provide a reference to determine landslide permeability coefficients and seepage.

Reinforced robotic bean optimization algorithm for cooperative target search of unmanned aerial vehicle swarm

AbstractIncreasing attention has been given to the utilization of swarm intelligent optimization algorithms to facilitate cooperative target search of unmanned aerial vehicle swarm (UAVs). However, there exist common issues associated with swarm intelligent optimization algorithms, which are low search efficiency and easy to trap in local optima. Simultaneously, the concentrated initial positioning of UAVs increase the probability of collisions between UAVs. To address these issues, this paper proposes a reinforced robotic bean optimization algorithm (RRBOA) aimed at enhancing the efficiency of UAVs for cooperative target search in unknown environments. Firstly, the algorithm employs a region segmentation exploration strategy to enhance the initialization of UAVs, ensuring a uniform distribution of UAVs to avoid collisions and the coverage capability of UAVs search. Subsequently, a neutral evolution strategy is incorporated based on the spatial distribution pattern of population, which aims to enhance cooperative search by enabling UAVs to freely explore the search space, thus improving the global exploration capability of UAVs. Finally, an adaptive Levy flight strategy is introduced to expand the search range of UAVs, enhancing the diversity of UAVs search and then preventing the UAVs search from converging to local optima. Experimental results demonstrate that RRBOA has significant advantages over other methods on nine benchmark simulations. Furthermore, the extension testing, which focuses on simulating pollution source search, confirms the effectiveness and applicability of RRBOA

Quantum Inspired Chaotic Salp Swarm Optimization for Dynamic Optimization

Many real-world problems are dynamic optimization problems that are unknown beforehand. In practice, unpredictable events such as the arrival of new jobs, due date changes, and reservation cancellations, changes in parameters or constraints make the search environment dynamic. Many algorithms are designed to deal with stationary optimization problems, but these algorithms do not face dynamic optimization problems or manage them correctly. Although some of the optimization algorithms are proposed to deal with the changes in dynamic environments differently, there are still areas of improvement in existing algorithms due to limitations or drawbacks, especially in terms of locating and following the previously identified optima. With this in mind, we studied a variant of SSA known as QSSO, which is integrating the principles of quantum computing. An attempt is made to improve the overall performance of standard SSA to deal with the dynamic environment effectively by locating and tracking the global optima for DOPs. This work is an extension of the proposed new algorithm QSSO, known as the Quantum-inspired Chaotic Salp Swarm Optimization (QCSSO) Algorithm, which is detailing the various approaches taken into consideration while solving DOPs. A chaotic operator is employed with quantum computing to respond to change and guarantee to increase individual searchability by improving population diversity and the speed at which the algorithm converges. We experimented by evaluating QCSSO on a well-known generalized dynamic benchmark problem (GDBG) provided for CEC 2009, followed by a comparative numerical study with well-regarded algorithms. As promised, the introduced QCSSO is discovered, and a rival algorithm for DOPs.

Transformer-based decoder of melanoma classification using hand-crafted texture feature fusion and Gray Wolf Optimization algorithm

Melanoma is a type of skin cancer that poses significant health risks and requires early detection for effective treatment. This study proposing a novel approach that integrates a transformer-based model with hand-crafted texture features and Gray Wolf Optimization, aiming to enhance efficiency of melanoma classification. Preprocessing involves standardizing image dimensions and enhancing image quality through median filtering techniques. Texture features, including GLCM and LBP, are extracted to capture spatial patterns indicative of melanoma. The GWO algorithm is applied to select the most discriminative features. A transformer-based decoder is then employed for classification, leveraging attention mechanisms to capture contextual dependencies. The experimental validation on the HAM10000 dataset and ISIC2019 dataset showcases the effectiveness of the proposed methodology. The transformer-based model, integrated with hand-crafted texture features and guided by Gray Wolf Optimization, achieves outstanding results. The results showed that the proposed method performed well in melanoma detection tasks, achieving an accuracy and F1-score of 99.54% and 99.11% on the HAM10000 dataset, and an accuracy of 99.47%, and F1-score of 99.25% on the ISIC2019 dataset.• We use the concepts of LBP and GLCM to extract features from the skin lesion images.• The Gray Wolf Optimization (GWO) algorithm is employed for feature selection.• A decoder based on Transformers is utilized for melanoma classification.

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.

NALA: a Nesterov accelerated look-ahead optimizer for deep learning.

Adaptive gradient algorithms have been successfully used in deep learning. Previous work reveals that adaptive gradient algorithms mainly borrow the moving average idea of heavy ball acceleration to estimate the first- and second-order moments of the gradient for accelerating convergence. However, Nesterov acceleration which uses the gradient at extrapolation point can achieve a faster convergence speed than heavy ball acceleration in theory. In this article, a new optimization algorithm which combines adaptive gradient algorithm with Nesterov acceleration by using a look-ahead scheme, called NALA, is proposed for deep learning. NALA iteratively updates two sets of weights, i.e., the 'fast weights' in its inner loop and the 'slow weights' in its outer loop. Concretely, NALA first updates the fast weights k times using Adam optimizer in the inner loop, and then updates the slow weights once in the direction of Nesterov's Accelerated Gradient (NAG) in the outer loop. We compare NALA with several popular optimization algorithms on a range of image classification tasks on public datasets. The experimental results show that NALA can achieve faster convergence and higher accuracy than other popular optimization algorithms.

Energy-saving diagnosis of public buildings based on multi-objective optimization algorithm

ABSTRACT This study focuses on existing ventilation, heating, and air conditioning systems in public buildings and mainly considers three objectives: system energy consumption, indoor thermal comfort, and efficiency. A multi-objective diagnosis system is established, which correlates evaluation indicators with key equipment, forming a clear hierarchical diagnosis system. Meanwhile, particle swarm optimization algorithm is combined with linear weighting method to optimize the operating parameters of key equipment based on the diagnosis results, obtaining the optimal parameters of various operating scenes. For winter conditions, the average system energy consumption is 34.2 W/m2, the average system energy efficiency ratio is 1.5, and the average indicator for indoor thermal environment is 1.06. For summer conditions, the average energy consumption of the systems is 28.9 W/m2, the average energy efficiency ratio is 2.2, and the average indicator for indoor thermal environment is – 0.82. Compared with the measured results, most of the optimized indicators are better, but the system energy efficiency ratio is slightly lower than the measured results for winter conditions. Through the established diagnosis system and optimization method, this research evaluates and optimizes the existing the systems in public buildings. Demonstrating the effectiveness of the established diagnosis system and optimization method.

Optimal design of graphene-based plasmonic enhanced photodetector using PSO

In this paper, we report a graphene-based plasmonic photodetector optimized using the particle swarm optimization (PSO) algorithm and compatible with complementary metal–oxide–semiconductor (CMOS) technology. The proposed photodetector structure is designed to minimize fabrication challenges and reduce production costs compared to more complex alternatives. Graphene has been used for its unique properties in the detection region, titanium nitride (TiN) as a CMOS-compatible metal, and both to aid in plasmonic excitation. Photodetectors have key parameters influenced by multiple independent variables. However, practical constraints prevent thorough adjustment of all variables to achieve optimal parameter values, often resulting in analysis based on several simplified models. Here we optimize these variables by presenting a new approach in the field of photodetectors using the capabilities of the PSO algorithm. As a result, for the proposed device at the wavelength of 1550 nm, the voltage responsivity is 210.6215 V/W, the current responsivity is 3.7213 A/W, the ultra-compressed length is less than 3μm\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mu {\ ext{m}}$$\\end{document}, and the specific detectivity is 2.566×107\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${10}^{7}$$\\end{document} Jones were obtained. Furthermore, the device in question works under the photothermoelectric effect (PTE) at zero bias and has zero dark current, which ultimately resulted in a very low noise equivalent power (NEP) of 4.5361 pW/Hz\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${\ ext{pW}}/\\sqrt{\ ext{Hz}}$$\\end{document}.

Multi-objective optimization strategy for the distribution network with distributed photovoltaic and energy storage

The randomness and fluctuation of large-scale distributed photovoltaic (PV) power will affect the stable operation of the distribution network. The energy storage system (ESS) can effectively suppress the power output fluctuation of the PV system and reduce the PV curtailment rate through charging/discharging states. In order to improve the operation capability of the distribution network and PV consumption rate, an optimal multi-objective strategy is proposed based on PV power prediction. First, the back propagation (BP) neural network with an improved genetic algorithm (GA) is used to predict PV power output. Furthermore, an adaptive variability function is added to the GA to improve the prediction accuracy. Then, the distribution network model containing distributed PV and the ESS is constructed. The optimal object contains network power loss, voltage deviation, and PV consumption. The model is solved based on the improved multi-objective particle swarm optimization (MOPSO) algorithm of Pareto optimality. The probabilistic amplitude is adopted to encode the particles for avoiding local optimal. Finally, the proposed optimal strategy is verified by the IEEE 33-bus distribution network. The results show that the proposed strategy has an obvious effect on reducing the network power loss and voltage deviation, as well as improving the PV consumption rate.

Harmonic Self-Compensation Control for Bidirectional Grid Tied Inverter Based on Crown Porcupine Optimization Algorithm

A self-compensating control strategy for harmonic parameters based on the crown porcupine optimization algorithm is proposed for the single-phase rectifier and two-phase inverter operation mode of the bidirectional converter. In order to improve the response speed of the inverter voltage, the instantaneous expressions of the phase angle coefficient and amplitude coefficient of the dc-side voltage doubling fluctuation are derived, and the third harmonic is calculated based on the crown porcupine optimization algorithm according to the Proportional Integral (PI) + Quasi-Proportional Resonance (QPR) double closed-loop control method and injected into the input voltage of the inverter side to offset the influence of the bus-doubling fluctuation on the output voltage of the two-phase inverters of B and C so that the total harmonic content of the two-phase output voltages of the two-phase inverters of B and C can be reduced. The total harmonic content of the B and C inverter output voltages is reduced. The effective control of the control method for single-phase rectifier two-phase inverter mode is verified through simulation. Finally, the effectiveness of the control strategy is verified by experimenting with a 15 kW LCL-type bi-directional converter prototype.

Optimized Energy Efficient- Hierarchical Clustering Based Routing (OEE-HCR) For Wireless Sensor Network (WSN)

The study into Wireless Sensor Network (WSN) has grown more crucial as a result of the many Internet of Things (IoT) applications. Energy – Harvesting (EH) technology can extend the lifespan of WSN; however, because the nodes would be difficult to get to during energy harvesting, an energy-efficient routing protocol should be developed. The use of clustering in this study balances energy consumption across all Sensor Node (SN) and reduces traffic and overhead throughout the data transmission phases of WSN. Cluster Head (CH) selection step of the Optimized Energy Efficient-Hierarchical Clustering Based Routing (OEE-HCR) technique involves sending data to the closest CH. In order to analyse and transmit each cluster data, CH will need to use more energy, which will hasten and asymmetrically deplete the network. Whale Optimization Algorithm (WOA) algorithm is introduced for the best number of clusters formation with dynamically selecting the CH. Experimentation analysis, results are measured using First Node Dead (FND), the Half Node Dead (HND), Last Node Dead (LND), and Maximum Lifetime Coverage (MLC) at the time of number of data transmission rounds performed in routing algorithms.

Multi-armed bandit algorithm for sequential experiments of molecular properties with dynamic feature selection.

Sequential optimization is one of the promising approaches in identifying the optimal candidate(s) (molecules, reactants, drugs, etc.) with desired properties (reaction yield, selectivity, efficacy, etc.) from a large set of potential candidates, while minimizing the number of experiments required. However, the high dimensionality of the feature space (e.g., molecular descriptors) makes it often difficult to utilize the relevant features during the process of updating the set of candidates to be examined. In this article, we developed a new sequential optimization algorithm for molecular problems based on reinforcement learning, multi-armed linear bandit framework, and online, dynamic feature selections in which relevant molecular descriptors are updated along with the experiments. We also designed a stopping condition aimed to guarantee the reliability of the chosen candidate from the dataset pool. The developed algorithm was examined by comparing with Bayesian optimization (BO), using two synthetic datasets and two real datasets in which one dataset includes hydration free energy of molecules and another one includes a free energy difference between enantiomer products in chemical reaction. We found that the dynamic feature selection in representing the desired properties along the experiments provides a better performance (e.g., time required to find the best candidate and stop the experiment) as the overall trend and that our multi-armed linear bandit approach with a dynamic feature selection scheme outperforms the standard BO with fixed feature variables. The comparison of our algorithm to BO with dynamic feature selection is also addressed.

Design-Optimization of Conventional Steel Structures for Realization of the Sustainable Development Objectives Using Metaheuristic Algorithm

The construction industry presents a significant environmental challenge due to its substantial environmental footprint, utilization of limited natural resources, and contribution to pollution and climate change. Additionally, optimizing the weight, cost, and duration of construction is crucial for enhancing serviceability, flexibility, efficiency, and profitability. In this research, the relationship between structure weight and other objective functions was explored using the single-objective gray wolf algorithm to investigate their impact on carbon footprint, water footprint, and construction time. Furthermore, employing a multi-objective optimization algorithm, a building structure was optimized for three systems featuring different structural frames based on the specified objective functions. The results revealed that the structure with intermediate steel moment-resisting frames exhibited the shortest construction time but incurred the highest construction cost. Conversely, the structure with intermediate steel moment-resisting frames with special steel concentric bracing demonstrated the lowest carbon footprint and water footprint among the studied structural frames. Consequently, the structure with intermediate steel moment-resisting frames with special concentric steel bracing was proposed as a green structure, emphasizing its environmentally friendly characteristics.

Hybridized soccer league-grey wolf Optimization algorithm and siamese network synergism based multimodal fusion scheme for prognosis of brain diseases

Hybridized soccer league-grey wolf Optimization algorithm and siamese network synergism based multimodal fusion scheme for prognosis of brain diseases

Enhanced Fuzzy-Based Super-Twisting Sliding-Mode Control System for the Cessna Citation X Lateral Motion

A novel combination of three control systems is presented in this paper: an adaptive control system, a type-two fuzzy logic system, and a super-twisting sliding mode control (STSMC) system. This combination was developed at the Laboratory of Applied Research in Active Controls, Avionics and AeroServoElasticity (LARCASE). This controller incorporates two methods to calculate the gains of the switching term in the STSMC utilizing the particle swarm optimization algorithm: (1) adaptive gains and (2) optimized gains. This methodology was applied to a nonlinear model of the Cessna Citation X business jet aircraft generated by the simulation platform developed at the LARCASE in Simulink/MATLAB (R2022b) for aircraft lateral motion. The platform was validated with flight data obtained from a Level-D research aircraft flight simulator manufactured by the CAE (Montreal, Canada). Level D denotes the highest qualification that the FAA issues for research flight simulators. The performances of controllers were evaluated using the turbulence generated by the Dryden model. The simulation results show that this controller can address both turbulence and existing uncertainties. Finally, the controller was validated for 925 flight conditions over the whole flight envelope for a single configuration using both adaptive and optimized gains in switching terms of the STSMC.

Monocular Depth Estimation Based on Dilated Convolutions and Feature Fusion

Depth estimation represents a prevalent research focus within the realm of computer vision. Existing depth estimation methodologies utilizing LiDAR (Light Detection and Ranging) technology typically obtain sparse depth data and are associated with elevated hardware expenses. Multi-view image-matching techniques necessitate prior knowledge of camera intrinsic parameters and frequently encounter challenges such as depth inconsistency, loss of details, and the blurring of edges. To tackle these challenges, the present study introduces a monocular depth estimation approach based on an end-to-end convolutional neural network. Specifically, a DNET backbone has been developed, incorporating dilated convolution and feature fusion mechanisms within the network architecture. By integrating semantic information from various receptive fields and levels, the model’s capacity for feature extraction is augmented, thereby enhancing its sensitivity to nuanced depth variations within the image. Furthermore, we introduce a loss function optimization algorithm specifically designed to address class imbalance, thereby enhancing the overall predictive accuracy of the model. Training and validation conducted on the NYU Depth-v2 (New York University Depth Dataset Version 2) and KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute) datasets demonstrate that our approach outperforms other algorithms in terms of various evaluation metrics.

Model-predictive space heating control for energy flexibility – a case study using a long short-term memory neural network surrogate model and a genetic optimization algorithm

This paper presents a case study where a model predictive control (MPC) logic is developed for energy flexible operation of a space heating system in an educational building. A Long Short-Term Memory Neural Network (LSTM) surrogate model is trained on the output of an EnergyPlus building simulation model. This LSTM model is used within an MPC framework where a genetic algorithm is used to optimize setpoint sequences. The EnergyPlus model is used to validate the performance of the control logic. The MPC approach leads to a substantial reduction in energy consumption (7%) and energy costs (13%) with improved comfort performance. Additional energy costs savings are possible (7–16%) if a sacrifice in indoor thermal comfort is accepted. The presented method is useful for developing MPC systems in the design stages where measured data is typically not available. Additionally, this study illustrates that LSTM models are promising for MPC for buildings.

Fine-tuning inflow prediction models: integrating optimization algorithms and TRMM data for enhanced accuracy

ABSTRACT This research explores machine learning algorithms for reservoir inflow prediction, including long short-term memory (LSTM), random forest (RF), and metaheuristic-optimized models. The impact of feature engineering techniques such as discrete wavelet transform (DWT) and XGBoost feature selection is investigated. LSTM shows promise, with LSTM-XGBoost exhibiting strong generalization from 179.81 m3/s RMSE (root mean square error) in training to 49.42 m3/s in testing. The RF-XGBoost and models incorporating DWT, like LSTM-DWT and RF-DWT, also perform well, underscoring the significance of feature engineering. Comparisons illustrate enhancements with DWT: LSTM and RF reduce training and testing RMSE substantially when using DWT. Metaheuristic models like MLP-ABC and LSSVR-PSO benefit from DWT as well, with the LSSVR-PSO-DWT model demonstrating excellent predictive accuracy, showing 133.97 m3/s RMSE in training and 47.08 m3/s RMSE in testing. This model synergistically combines LSSVR, PSO, and DWT, emerging as the top performers by effectively capturing intricate reservoir inflow patterns.