Hybrid Optimization Strategy Research Articles

Knowledge-assisted hybrid optimization strategy of large-scale crude oil scheduling integrated production planning

As modern refinery crude oil scheduling scales up, traditional manual operations and independent optimization methods struggle with complexity and dynamics. This study proposes an empirically assisted integrated planning and scheduling optimization model.The integrated model is solved using a hybrid optimization algorithm combining mathematical programming and particle swarm optimization (MP/PSO). Long-term planning aims to minimize operational and transportation costs while maximizing refinery profits; short-term scheduling, based on initial long-term plans, aims to minimize unit switchovers. In the short-term scheduling phase, heuristic rules based on empirical operational knowledge generate a high-performing initial population to accelerate convergence. This strategy is crucial for enhancing refinery emergency response capabilities, ensuring stable operations, and improving economic benefits. Experimental results show that within a reasonable time frame, MP/PSO performs better than PSO and manual scheduling in large-scale crude oil scheduling scenarios.

A novel hybrid genetic algorithm and Nelder-Mead approach and it’s application for parameter estimation

Background Traditional optimization methods often struggle to balance global exploration and local refinement, particularly in complex real-world problems. To address this challenge, we introduce a novel hybrid optimization strategy that integrates the Nelder-Mead (NM) technique and the Genetic Algorithm (GA), named the Genetic and Nelder-Mead Algorithm (GANMA). This hybrid approach aims to enhance performance across various benchmark functions and parameter estimation tasks. Methods GANMA combines the global search capabilities of GA with the local refinement strength of NM. It is first tested on 15 benchmark functions commonly used to evaluate optimization strategies. The effectiveness of GANMA is also demonstrated through its application to parameter estimation problems, showcasing its practical utility in real-world scenarios. Results GANMA outperforms traditional optimization methods in terms of robustness, convergence speed, and solution quality. The hybrid algorithm excels across different function landscapes, including those with high dimensionality and multimodality, which are often encountered in real-world optimization issues. Additionally, GANMA improves model accuracy and interpretability in parameter estimation tasks, enhancing both model fitting and prediction. Conclusions GANMA proves to be a flexible and powerful optimization method suitable for both benchmark optimization and real-world parameter estimation challenges. Its capability to efficiently explore parameter spaces and refine solutions makes it a promising tool for scientific, engineering, and economic applications. GANMA offers a valuable solution for improving model performance and effectively handling complex optimization problems.

Integrating neural networks with advanced optimization techniques for accurate kidney disease diagnosis

Kidney diseases pose a significant global health challenge, requiring precise diagnostic tools to improve patient outcomes. This study addresses this need by investigating three main categories of renal diseases: kidney stones, cysts, and tumors. Utilizing a comprehensive dataset of 12,446 CT whole abdomen and urogram images, this study developed an advanced AI-driven diagnostic system specifically tailored for kidney disease classification. The innovative approach of this study combines the strengths of traditional convolutional neural network architecture (AlexNet) with modern advancements in ConvNeXt architectures. By integrating AlexNet’s robust feature extraction capabilities with ConvNeXt’s advanced attention mechanisms, the paper achieved an exceptional classification accuracy of 99.85%. A key advancement in this study’s methodology lies in the strategic amalgamation of features from both networks. This paper concatenated hierarchical spatial information and incorporated self-attention mechanisms to enhance classification performance. Furthermore, the study introduced a custom optimization technique inspired by the Adam optimizer, which dynamically adjusts the step size based on gradient norms. This tailored optimizer facilitated faster convergence and more effective weight updates, imporving model performance. The model of this study demonstrated outstanding performance across various metrics, with an average precision of 99.89%, recall of 99.95%, and specificity of 99.83%. These results highlight the efficacy of the hybrid architecture and optimization strategy in accurately diagnosing kidney diseases. Additionally, the methodology of this paper emphasizes interpretability and explainability, which are crucial for the clinical deployment of deep learning models.

Dynamic parameter identification of modular robot manipulators based on hybrid optimization strategy: genetic algorithm and least squares method

Dynamic parameter identification of modular robot manipulators based on hybrid optimization strategy: genetic algorithm and least squares method

Research, Analysis, and Improvement of Unmanned Aerial Vehicle Path Planning Algorithms in Urban Ultra-Low Altitude Airspace

Urban ultra-low altitude airspace (ULAA) presents unique challenges for unmanned aerial vehicle (UAV) path planning due to high building density and regulatory constraints. This study analyzes and improves classical path planning algorithms for UAVs in ULAA. Experiments were conducted using A*, RRT, RRT*, and artificial potential field (APF) methods in a simulated environment based on building data from Chengdu City, China. Results show that traditional algorithms struggle in dense obstacle environments, particularly APF due to local minima issues. Enhancements were proposed: a density-aware heuristic for A*, random perturbation for APF, and a hybrid optimization strategy for RRT*. These modifications improved computation time, path length, and obstacle avoidance. The study provides insights into the limitations of classical algorithms and suggests enhancements for more effective UAV path planning in urban environments.

Optimal Control Problems in Complex Systems: The Combination of Mathematical Modeling and Optimization Strategies

Optimal control in complex systems is a challenging and practical field. Traditional control methods can not meet the needs of complex systems, so mathematical modeling and optimization strategies are needed to improve system performance and stability. The optimal control theory can solve the control problem in complex system effectively and improve the operation efficiency of the system by establishing mathematical model and combining optimization strategy. From mathematical modeling method to hybrid optimization strategy research, this paper discusses the theory and practice of optimal control in depth. In the future, it is necessary to further improve the research methods to solve the uncertainty of complex system models and make greater contributions to realizing more intelligent control schemes.

Hybrid YSGOA and neural networks based software failure prediction in cloud systems

In the realm of cloud computing, ensuring the dependability and robustness of software systems is paramount. The intricate and evolving nature of cloud infrastructures, however, presents substantial obstacles in the pre-emptive identification and rectification of software anomalies. This study introduces an innovative methodology that amalgamates hybrid optimization algorithms with Neural Networks (NN) to refine the prediction of software malfunctions. The core objective is to augment the purity metric of our method across diverse operational conditions. This is accomplished through the utilization of two distinct optimization algorithms: the Yellow Saddle Goat Fish Algorithm (YSGA), which is instrumental in the discernment of pivotal features linked to software failures, and the Grasshopper Optimization Algorithm (GOA), which further polishes the feature compilation. These features are then processed by Neural Networks (NN), capitalizing on their proficiency in deciphering intricate data patterns and interconnections. The NNs are integral to the classification of instances predicated on the ascertained features. Our evaluation, conducted using the Failure-Dataset-OpenStack database and MATLAB Software, demonstrates that the hybrid optimization strategy employed for feature selection significantly curtails complexity and expedites processing

A novel squirrel-cat optimization based optimal expansion planning for distribution system

AimIn recent years, renewable distributed generation (DG) has grown to deliver sustainable electricity with minimal environmental impact. However, renewable DG poses new provocation in the distribution system expansion planning problem (DSEP). To address those problems, this paper suggests a new mathematical model for distribution system expansion plans using a novel hybrid optimization strategy. MethodThe optimal expansion plan for the distribution system is achieved using the hybrid optimization model, named Squirrel Search Insisted Cat Swarm Optimization (SSI-CS) algorithm. The proposed hybrid optimization algorithm is developed with the incorporation of the characteristics features of Squirrel search optimization (SSA) algorithm and Cat Swarm Optimization (CSO) Algorithm to optimize the solar capacity, wind capacity and biomass capacity. This combination aims to strike a balance between global and local optimization, ultimately leading to better cost-effective results. The Distribution systems variables like DG type, size/capacity, location, real power, reactive power, and the solar and wind capacity during load demand uncertainty act as the input to the proposed hybrid optimization algorithm. The main objective of attaining minimal cost for the expansion plan of the distribution system is checked, and the cycle is repeated until obtaining the optimal solution (minimum cost). ResultThe experimental analysis using an IEEE-33 bus system with 5 system states is executed in MATLAB/Simulink. The suggested SSI-CS model attained a minimal operational cost of 7433.4 which better than GWO, SSA and CSO. ConclusionHence, the proposed SSI-CS shows promise as an efficient and effective approach for distribution system expansion planning.

Design of Novel Brain Tumor Segmentation System Using Hybrid Heuristic-Aided Multiscale Self-Guided Attention Mechanism-Based Adaptive Unet+++ with 3D Brain MRI Images

Segmentation of brain tumors attains great importance in the medical industry. As the brain tumor causes an earlier death, detection and diagnosis are required. Generally, brain tumor diagnosis is done by considering Magnetic Resonance Imaging (MRI) because it has superficial feature information. In the existing works, the different segmentation process is analyzed, yet it is more time-consuming, and has complexities. Thus, building of an efficient segmentation model is a quite challenging task. As the former implemented models are not in place to segment the abnormal region properly, it suggests developing an effective automated model using recently emerged techniques of deep learning. To surmount such challenging factors, a novel 3D brain tumor segmentation model is proposed with hybrid heuristic development. Initially, the brain images are collected from the standard benchmark datasets. The collected brain images are pre-processed using the adaptive technique of Contrast Limited Adaptive Histogram Equalization (CLAHE). The pre-processed images are segmented with the developed Multiscale Self-Guided Attention Mechanism-based Adaptive UNet3[Formula: see text] (MSGAM-AUNet3[Formula: see text]), where the parameters are optimized with the hybrid optimization strategy of Modified Path Finder Coyote Optimization (MPFCO) to elevate the segmentation performance. The experimental analysis is carried out to estimate the efficiency of the developed framework with the comparison using diverse segmentation techniques.

A Novel Supercapacitor Model Parameters Identification Method Using Metaheuristic Gradient-Based Optimization Algorithms

This paper addresses the critical role of supercapacitors as energy storage systems with a specific focus on their modeling and identification. The lack of a standardized and efficient method for identifying supercapacitor parameters has a definite effect on widespread adoption of supercapacitors, especially in high-power density applications like electric vehicle regenerative braking. The study focuses on parameterizing the Zubieta model for supercapacitors, which involves identifying seven parameters using a hybrid metaheuristic gradient-based optimization (MGBO) approach. The effectiveness of the MGBO method is compared to the existing particle swarm optimization (PSO) and to the following algorithms proposed and developed in this work: ‘modified MGBO’ (M-MGBO) and two PSO variations—one combining PSO and M-MGBO and the other incorporating a local escaping operator (LCEO) with PSO. Metaheuristic- and gradient-based algorithms are both affected by problems associated with locally optimal results and with issues related to enforcing constraints/boundaries on solution values. This work develops the above-mentioned innovations to the MGBO and PSO algorithms for addressing such issues. Rigorous experimentation considering various types of input excitation provides results indicating that hybrid PSO-MGBO and PSO-LCEO outperform traditional PSO, showing improvements of 51% and 94%, respectively, while remaining comparable to M-MGBO. These hybrid approaches effectively estimate Zubieta model parameters. The findings highlight the potential of hybrid optimization strategies in enhancing precision and effectiveness in supercapacitor model parameterization.

Optimal allocation of controllable power factor distributed generation with network reconfiguration on electric vehicle charging station loaded distribution network

This paper presents a hybrid optimisation technique to solve the problem of optimal allocation of controllable power factor Distributed Generators (DGs) together with network reconfiguration on Electric Vehicle Charging Stations (EVCSs)-loaded distribution networks. The suggested hybrid optimisation strategy combines the Artificial Gorilla Troops Optimizer (GTO) algorithm with genetic operators to improve convergence characteristics and prevent premature convergence to local optima. The objective is to minimise power loss, bus voltage deviation and voltage stability index reduction, which are formulated as a multi-objective function. The effectiveness of the proposed approach is evaluated on 69 and 118-bus distribution networks. Additionally, a comparative analysis is performed to evaluate the efficacy of the suggested approach in comparison with standard GTO and other well-known optimisation algorithms. The results demonstrate that simultaneous optimal placement of controllable power factor DGs with network reconfiguration demonstrates superior effectiveness in mitigating the adverse impact of EVCSs on distribution networks compared to optimisation of fixed-power factor DG placement with network reconfiguration. Furthermore, the hybrid optimisation approach outperforms other applied algorithms in terms of solution quality.

Power Quality Conditioners-Based Fractional-Order PID Controllers Using Hybrid Jellyfish Search and Particle Swarm Algorithm for Power Quality Enhancement

Power quality (PQ) is a major issue in today’s electrical system that affects both utilities and customers. The proliferation of power electronics devices, smart grid technology, and renewable energy sources (RES) have all contributed to the emergence of PQ concerns in today’s power system. The Unified Power Quality Conditioner (UPQC) is a versatile tool that can be used to fix distribution grid issues caused by irregular voltage, current, or frequency. Several tuning parameters, however, restrict the effectiveness of the Fractional-Order Proportional Integral Derivative (FOPID) control technique, which is proposed to improve UPQC performance. To move beyond these restrictions and find the optimal solution for the FOPID controller problem, a hybrid optimization strategy called the Hybrid Jellyfish Search Optimizer and Particle Swarm Optimizer (HJSPSO) is employed. To meet the load requirement during PQ issue periods, the suggested model incorporates a renewable energy source into the grid system. Whether the load is linear or non-linear, the design maintains PQ problems to a minimum. Furthermore, the FOPID control technique is compared with other controllers. Results show that grid-connected RES systems using the proposed FOPID control approach for UPQC have fewer PQ problems. The presented UPQC with HJSPSO strategy significantly outperformed, with the shortest computing time of 127.474 s and an objective function value of 1.423.

Hybrid optimization strategy for water cooling system: enhancement of photovoltaic panels performance

Abstract Solar energy is the most effective substitute for fossil fuels when it comes to Produce electricity among the numerous renewable energy sources. The efficiency may drop as a result of overheating, and the PV cell may also be harmed. Therefore, increasing the output of a solar PV system at a lower cost is essential to improving its efficiency. Additionally, by using cooling methods, the PV cells’ lifetime is extended. By lowering the working temperature of a PV panel’s surface, you may increase efficiency and slow the thermal deterioration rate. This may be done by module cooling and lowering the heat that the PV cells generate while operating. Hence, an active cooling technology known as optimization-aided water spraying technique is employed to increase efficiency. This method enables the PV panels to provide their maximum output power while taking less time to drop down to a lower surface temperature. Beluga Whale assisted Jellyfish Optimization (BWJO) model is suggested as a means of achieving these goals. Finally, Simulink/MATLAB is used to implement the suggested method and optimize the PV system cooling. The performances of the two components were compared using a variety of metrics.

Application of Adaptive Algorithms in Smart Building Design Optimisation

Abstract How to realize the unity of safety, comfort, and economy of building structures has been a hot spot of concern in the field of construction engineering. This paper searches for optimal particles using a hybrid optimization strategy and optimizes the weights of each index in the fitness function into the same interval. Then dynamic inertia weights are used to improve the performance of the algorithm, and an enhanced adaptive particle swarm algorithm is obtained. After selecting the optimization variables for the building design, the objective function and constraints are designed, and the improved particle swarm algorithm is used to solve the optimal design of the intelligent building. The total weight of the target building structure was reduced after optimization, and 47.04% of the building materials were saved. The outer diameter of the steel pipe concrete at the lowest level of the building increases from 1.73m to 2.06m after optimization, which fulfills the law of column change in building design. It has also been found that the wind resistance of the optimized building structure has improved. This paper provides a reliable basis for the application of adaptive algorithms in building design optimization, and the proposed method also provides an effective reference for the field of construction engineering.

An Adaptive Hybrid Optimization Strategy for Resource Allocation in Network Function Virtualization

An Adaptive Hybrid Optimization Strategy for Resource Allocation in Network Function Virtualization

Software Testing Using Cuckoo Search Algorithm with Machine Learning Techniques

Software testing are any errors, flaws, bugs, mistakes, failures in a piece of software that might cause the programme to produce incorrect or unexpected results. Testing in software almost always increase both the time and money needed to finish a project. And finding bugs and fixing them is a laborious and expensive software process in and of itself. While it's unrealistic to expect to completely eradicate all testing from a project, their severity may be mitigated. It is possible to predict where bugs may appear in software using a method known as software defect prediction (SDP). The goal of each software development project should be to provide a bug-free product. Predicting where bugs may appear in code, often known as software defect prediction (SDP), is an important part of fixing software. Software of a high calibre should have few bugs. A software metric is a quantitative or qualitative evaluation of some aspect of the programme or its requirements. One of the more recent population-based algorithms, Cuckoo Search (CS) was inspired by the flight patterns of some cuckoo species as well as the Lévy flying patterns of other birds and fruit flies. The needs for international convergence are met by CS. KNN is a significant non-parameter supervised learning technique. This paper presents an overview of Stochastic Diffusion Search (SDS) in the form of a social metaphor to illustrate the processes by which SDS allots resources. The best-fit pattern identification and matching difficulties were addressed by SDS using a novel probabilistic method. As a multiagent population-based global search and optimization method, SDS is a distributed model of computing that makes use of interaction amongst basic agents. The behaviour of SDS is described by studying its resource allocation, convergence to global optimum, resilience, minimum convergence criterion, and linear time complexity within a rigorous mathematical framework, setting it apart from many nature-inspired search algorithms. This paper proposes a hybrid optimization strategy based on CS-SDS techniques. By using the global search strategy solution of the SDS algorithm, this hybridization idea aims to enhance the cuckoo bird's search strategy for the optimum host nest. To that end, the SDS method would be used to place the cuckoo egg in the most advantageous location. When compared to other classifiers, PC2's improved performance may be attributed to its higher recall values. When compared to the Naive Bayes and Radial Bias Neural Network classifiers, the KNN performs 7.64% and 2.20% better, respectively.

Optimal Placement of Battery Swapping Stations for Power Quality Improvement: A Novel Multi Techno-Economic Objective Function Approach

In recent years, battery swapping stations have become increasingly popular in smart energy networks. Its advantages include reducing the time required for recharging energy, balancing the grid’s load, and extending the battery’s lifespan. Despite efforts focused on the placement and operation of battery swapping stations (BSSs), there is still a lack of a comprehensive and systematic examination that covers all aspects of both the economic and technical aspects of the power network. This encompasses considerations such as power quality and reliability, particularly in terms of where these stations should be located. This paper introduces a novel framework for strategically positioning BSS within smart microgrids that integrate distributed energy resources (DERs). It takes into account various technical factors (such as reliability and power quality) and economic factors (like the cost of generation and operation), which have been overlooked in the previous research. To achieve this goal, a unique hybrid optimization strategy is developed, incorporating a combination of epsilon-constraint and lexicographic (DECL) optimization methods. This approach tackles a multi-objective challenge, treating factors like the number, locations, and sizes of BSS as independent variables, while operational costs and technical power quality metrics are considered dependent variables. To validate this approach, it is tested on standard benchmark distribution power networks such as IEEE 33, 69, and 118 bus systems. The simulation results, showcasing the strengths and capabilities of this innovative strategy, are compared to the findings of previous research studies.

Towards the saving potentials using a hybrid topology optimization: Application of a coupled deterministic and empirical approach solving a geotechnical optimization problem

AbstractThis article presents the application of the TOSS (topology optimization for stiffness and strength) algorithm, a hybrid optimization strategy for topology optimization, used for the design of a strip foundation as a basic geotechnical structure. One of the challenges of this field is to improve structural performance by using less material than conventional structures. Therefore, the SIMP (solid isotropic material with penalization) is applied to optimize the foundation concerning its deformational behavior. The downstream SKO (soft kill option) then solves for optimality concerning the foundation's stress distribution. Numerical experiments with the TOSS algorithm reveal great potential for material savings. The coupled solution presents the benefit of reducing emissions due to material savings of more than 20% in comparison to the individual SIMP and SKO algorithms. A positive by‐product of the method is that stress peaks under the foundation are reduced due to the homogenization of stresses as a result of SKO optimization, thus creating the conditions for better durability of the foundation.

Contingency-resilient PMU placement using Fuzzy Logic and Discrete Artificial Bee Colony algorithm for comprehensive network observability

In transforming traditional grid systems into intelligent and microgrid-based systems, the Phasor Measurement Units (PMUs) play a prominent role in enhancing monitoring, assessment, control, and protection by estimating voltage and current phasors correctly and quickly. However, since PMUs are not cost-effective, the decision to take the requisite number and their placement is a significant issue and needs to focus on a better approach. This study addresses the solution methodology to compute the optimal locations of a reduced PMU number to have complete network observability. A new hybrid optimization strategy based on the Fuzzy Logic (FL) and Discrete Artificial Bee Colony (DABC) algorithm has been suggested. The suggested method is titled FL-DABC algorithm, which has been applied to determining the optimal placement of PMUs in microgrid-based systems. The suggested approach tackles the problem of fully network-observable cost-effective PMU deployment. The effectiveness of the Algorithm is evaluated through simulations under various operating limitations, such as zero injection buses, a single PMU, and line outage scenarios. A topological observability analysis validates full network observability with the computed PMU placement. The study also includes branch PMU placement set computation and a comparative analysis with other techniques using standard IEEE test networks for simulations.

STR: Hybrid Tensor Re-Generation to Break Memory Wall for DNN Training

With the growth of the depth of neural networks and the scale of data, the difficulty of network training also increases. When the GPU memory is insufficient, it is challenging to train deeper models. Recent research uses tensor swapping and recomputation techniques in a combined manner to optimize memory usage. However, complex dependencies and enormous scales of the DNN graph limit the improvement of single GPU memory optimization. Improper swap and recomputation decisions even bring negative effects on training performance. In this paper, we propose a novel hybrid tensor re-generation strategy, called STR, which combines swap and recomputation techniques to find the optimal execution plan for the DNN training when the memory is limited. We formalize our memory optimization problem with constraints that describe the dependency of the operator calculation and the bandwidth usage of the swap. A <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">host checkpoint</i> mechanism is designed to make full use of the swapped tensors, which reduces the cost of the recomputation. We also present a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">recursive source tracing</i> algorithm to improve the optimization efficiency by constraint relaxation with a performance bound. To optimize large models, we further introduce an approximation method based on a weighted graph coarsening. We implement a prototype of STR as a plugin on TensorFlow and evaluated based on 5 popular DNN models. The experimental result shows that the approximate solution of STR improves the training throughput of ResNet series of models by up to 28.1% compared to the state-of-the-art hybrid optimization strategy.