Combining Particle Swarm Optimization Research Articles

Optimal dispatch of integrated energy system with P2G considering carbon trading and demand response.

How to maintain the economic and low-carbon operation of the integrated energy system (IES) while taking into account the interests of the user side is of great significance to promote the large-scale development of IES. For this reason, this paper takes IES with the electricity-to-gas device as the research object and first constructs a demand response model that takes into account the user's energy experience and a reward and punishment ladder carbon trading model. Second, an IES game optimization framework considering carbon trading and demand response is proposed. On this basis, taking the operators and users of the integrated energy system as the main players of the game, a two-level game optimization scheduling model is constructed to synchronously improve the economic, low-carbon, and satisfactory operation of IES, and the proposed model is solved by the combination of particle swarm optimization and CPLEX. Finally, the simulation shows that the proposed model can effectively enhance the benefits of both supply and demand while reflecting the user response behavior more realistically.

Particle swarm optimization‐XGBoost‐based modeling of radio‐frequency power amplifier under different temperatures

AbstractXGBoost is the optimization of gradient boosting with the best overall performance among machine learning algorithms. By introducing a regularization term into the loss function of gradient boosting, XGBoost can effectively limit the complexity of the model, improve the generalization ability, and solve the overfitting problem. In this paper, XGBoost is first introduced into modeling radio‐frequency (RF) power amplifiers (PA) under different temperatures. Furthermore, the modeling effect of XGBoost is mainly dependent on hyperparameters. As traditional grid search is time‐consuming and labor‐intensive, this paper combines particle swarm optimization (PSO) with XGBoost for searching hyperparameters. The experimental results show that XGBoost can effectively suppress the overfitting problem in gradient boosting while modeling RF PAs in different ambient temperatures. In addition, compared to classic machine learning algorithms, including support vector regression (SVR), gradient boosting, and XGBoost, the proposed PSO‐XGBoost can increase the modeling accuracy by one order of magnitude or more while also increasing the modeling speed by more than one magnitude or more. The PSO‐XGBoost model proposed in this paper can be introduced into modeling other microwave/RF devices and circuits to improve modeling accuracy and reduce modeling time.

A novel hybrid optimization framework for sizing renewable energy systems integrated with energy storage systems with solar photovoltaics, wind, battery and electrolyzer-fuel cell

This study proposes a novel approach to evaluate the integration of solar photovoltaic (PV) and wind turbine renewable energy systems (RES) with Electrolyzer-Fuel Cell Energy Storage System (EFCS) and Battery Energy Storage System (BESS). The objective is to minimize the weighted average cost of energy (waCOE) while maintaining a specific renewable energy fraction (FRES). To achieve this objective, a new hybrid optimization system that combines Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) is proposed to simultaneously optimize the capacity of PV, wind turbine, battery, electrolyzer, hydrogen tank, and fuel cell, which makes it a complex and nonlinear optimization problem. The proposed method produces more practical outcomes by implementing some constraints on PSO and strengthens its ability to exploit optimization opportunities. Six scenarios representing different integrated systems are investigated and compared technically and economically, including PV + BESS, PV + EFCS, Wind + BESS, Wind + EFCS, PV + Wind + BESS, and PV + Wind + EFCS. A case study is conducted on a university campus situated on a Mediterranean island, where electricity production relies on imported fossil fuel. The findings indicate that a PV-wind hybrid system consisting of a 1.15 MW wind turbine, a 2.89 MW PV, and a 2.31 MWh BESS has the lowest waCOE of 0.1838 €/kWh. This system is capable of providing a demand–supply fraction (DSF) of 44.63% with a FRES of 60.1%. The study found that a hybrid system consisting of PV and wind turbines showed promise in the examined region due to their complementary characteristics. Additionally, combining various RES with BESS with approximately 33–35% lower waCOE was found to be more economically viable and resulted in 16–20% higher DSF compared to EFCS.

Bi-level and multi-objective optimization of renewable energy sources and storage planning to support existing overloaded electricity grids

The paper proposes a bi-level multi-objective optimization model to optimally design and operate renewable energy sources and storage systems in an existing electrical grid with increasing demand. while respecting network constraints based. The bi-level optimization model combines particle swarm optimization (PSO) and dynamic linear AC-optimal power flow (DLOPF). The aim of the bi-objective model is to minimize costs while limiting carbon emissions. PSO sizes and identifies the placement of battery energy storage (BES) systems, and DLOPF locates and sizes RES in a spatial–temporal framework using the Levelized Cost of Energy and Storage. Different scenarios were applied to the IEEE-30 bus system to reveal the behavior of the dynamic network for the different cases, and the associated effect of integrating RES and BES. The model resulted in optimized scenarios in terms of placement and sizing of RES and BES at the lowest cost while considering cost minimization and carbon constraints. This shows how the complexity of the CO2 constraints requires more RES and BES installations and thus more funds. The maximum CO2 limit achieved is 30%, which has reached the storage limits and increased the overall cost by $15 m.

Load Frequency Control Using the Particle Swarm Optimisation Algorithm and PID Controller for Effective Monitoring of Transmission Line

Load frequency control (LFC) plays a critical role in maintaining the stability and reliability of the power system. With the increasing integration of renewable energy sources and the growth of complex interconnected grids, efficient and robust LFC strategies are in high demand. In recent years, the combination of particle swarm optimisation (PSO) and proportional-integral-derivative (PID) controllers, known as PSP-PID, has been used as a promising approach to enhance the performance of LFC systems. This article focuses on modelling, simulation, optimisation, advanced control techniques, expert knowledge, and iterative refinement of the power system to help achieve suitable PID settings that provide reliable control of the load frequency in the transmission line. The performance indices of the proposed algorithm are measured by the integral time absolute error (ITAE), which is 0.0005757 with 0.9994 Ki, 0.7741 Kp, and 0.1850 Kd. The model system dynamics are tested by varying the load frequency from 300 MW to 350 MW at a load variation of 0.2. The suggested controller algorithm is relatively reliable and accurate in power system management and protection load frequency control compared to conventional methods. This work can be improved by including more generating stations synchronised into a single network.

Optimal Selection of the Cluster Head in Wireless Sensor Networks by Combining Particle Swarm Optimization and Efficient Genetic Algorithm

Wireless Sensor Networks (WSNs) have become a crucial component of numerous applications, including the military, healthcare, and environmental monitoring. A promising approach to increasing the lifespan of the sensor network is cluster-based WSNs. In WSNs, choosing the best cluster head is a crucial task that has an impact on the network's performance and energy efficiency. There are various issues with current methods for choosing the cluster head, including nodes dying too soon, uneven energy usage, and shorter network lifetimes. Moreover, traditional methods such as Randomized Clustering and Fixed Cluster Head are not effective in prolonging the network lifetime as they do not consider the energy consumption and residual energy of nodes. In this paper, an optimal selection of cluster head is presented where we combine the Particle Swarm Optimization (PSO) and Efficient Genetic Algorithm (EGA). Firstly, PSO is used to randomly select the cluster head and update the position of each cluster. Thereafter, EGA invokes its fitness values to select the best cluster head that transmits information to the base station. The simulation result shows that the performance improvement of the proposed method PSO_EGA in terms of network lifetime is 0.10% against Improve Cuckoo Search Algorithm (ICSA) and 0.20% against Hybrid Crow Search Algorithm (HCSA), packet to cluster head is 7% against ICSA and 16% against HCSA, packet to sink is 11% against ICSA and 22% against HCSA and number of alive node is 28% against ICSA and 48% against HCSA. Therefore, our proposed method outperforms ICSA and HCSA in terms of the aforementioned parameters.

Hierarchical optimal scheduling method for regional integrated energy systems considering electricity-hydrogen shared energy

Shared energy storage is widely recognized as an energy hub for the coordinated operation of regional integrated energy systems (RIESs). Multi-energy systems (MESs) share centralized energy storage to store excess renewable energy sources (RESs). This paper proposes a novel energy-sharing framework considering hydrogen trading, which is suitable for residential, industrial, and commercial RIES structures. Shared energy storage operator (SESO) promotes hydrogen energy transactions by formulating time-of-use (TOU) hydrogen prices. The proposed hydrogen energy trading method can be regarded as a master-client structure, and a hierarchical optimal scheduling method based on the Stackelberg game relationship is designed. Finally, a case study is performed based on an optimal scheduling algorithm combining particle swarm optimization (PSO) and mixed integer linear programming (MILP). The cases show the electricity‑hydrogen shared energy storage mechanism in RIESs can improve the RESs utilization rate and effectively reduce the operating costs of each system. Moreover, compared with RIESs with a single centralized electric energy storage, the TOU hydrogen price mechanism can further lower the energy prices and improve the economy of the RIES. The cases show that hydrogen energy sharing reduces the operating cost of RIES by 9.96% and increases the regional energy utilization rate by 2.97%. And the shared energy storage business model can satisfy the economy of both SESO and RIES. It confirms the rationality of the electric hydrogen shared energy storage project.

A robust identification procedure for phase field fracture mechanics parameters

The classical Phase Field (PF) model for fracture mechanics of brittle materials based on the finite element method involves three parameters in addition to the Poisson ratio ν: the Young’s modulus E, the fracture toughness Gc, and the internal length scale lc. The latter is mathematically conceived as a numerical regularization parameter that should tend to zero to recover linear elastic fracture mechanics (LEFM) predictions. To address this issue, a robust algorithm is implemented in MATLAB, which combines Particle Swarm Optimization (PSO) and the Phase Field (PF) approach to fracture based on the finite element method. The algorithm has been applied to a series of uni-axial tensile tests (with E and lc to be identified) and to three-point bending tests (with E, lc and also Gc to be identified) on specimens made of ABS material. Results show that the optimal values of E and Gc are consistent in both tests, while lc presents a significant dependency upon the test type. Therefore, different values of the internal length scale should be identified and used to match the experimental responses under uni-axial tension or bending.

A Feature Construction Method That Combines Particle Swarm Optimization and Grammatical Evolution

The problem of data classification or data fitting is widely applicable in a multitude of scientific areas, and for this reason, a number of machine learning models have been developed. However, in many cases, these models present problems of overfitting and cannot generalize satisfactorily to unknown data. Furthermore, in many cases, many of the features of the input data do not contribute to learning, or there may even be hidden correlations between the features of the dataset. The purpose of the proposed method is to significantly reduce data classification or regression errors through the usage of a technique that utilizes the particle swarm optimization method and grammatical evolution. This method is divided into two phases. In the first phase, artificial features are constructed using grammatical evolution, and the progress of the creation of these features is controlled by the particle swarm optimization method. In addition, this new technique utilizes penalty factors to limit the generated features to a range of values to make training machine learning models more efficient. In the second phase of the proposed technique, these features are exploited to transform the original dataset, and then any machine learning method can be applied to this dataset. The performance of the proposed method was measured on some benchmark datasets from the relevant literature. Also, the method was tested against a series of widely used machine learning models. The experiments performed showed a significant improvement of 30% on average in the classification datasets and an even greater improvement of 60% in the data fitting datasets.

An Efficient Hybrid Particle Swarm and Gradient Descent Method for the Estimation of the Hosting Capacity of Photovoltaics by Distribution Networks

With many distribution networks adopting photovoltaic (PV) generation systems in their networks, there is a significant risk of over-voltages, reverse power flow, line congestion, and increased harmonics. Therefore, there is a need to estimate the amount of PV that can be injected into the distribution network without pushing the network towards these threats. The largest amount of PV a distribution system can accommodate is the PV hosting capacity (PVHC). The paper proposes an efficient method for estimating the PVHC of distribution networks that combines particle swarm optimization (PSO) and the gradient descent algorithm (GD). PSO has a powerful exploration of the solution space but poor exploitation of the local search. On the other hand, GD has great exploitation of local search to obtain local optima but needs better global search capabilities. The proposed method aims to harness the advantages of both PSO and GD while alleviating the ills of each. The numerical case studies show that the proposed method is more efficient, stable, and superior to the other meta-heuristic approaches.

Order planning with an outsourcing strategy for a make-to-order/make-to-stock production system using particle swarm optimization with a self-adaptive genetic operator

This paper proposes an order planning method for an MTO-MTS (make-to-order/make-to-stock) production system, where semi-finished products are produced in advance to shorten the fulfillment lead time for customer orders. The semi-finished products can be either produced in-house or outsourced from an outside supplier. To minimize the outsourcing cost and the total penalty cost for the order planning, we build an integer programming model to jointly optimize the inventory matching, multi-process production, and outsourcing for both finished and semi-finished product orders. Because the problem is NP-hard, we propose a heuristic algorithm, APSO-SGO, that combines particle swarm optimization (PSO) and a self-adaptive genetic operator (SGO) based on measuring the swarm’s degree of aggregation (“A”) to solve it. Specifically, we first define four metrics to calculate the swarm’s degree of aggregation and determine whether the PSO is trapped in a local optimum. Self-adaptive crossover and mutation operations are then applied to improve the algorithm’s global search based on the current state of the PSO and the particles’ quality. To assess the method, we conduct numerical experiments using multiple datasets from a steel factory. The results demonstrate the effectiveness of our model and algorithm. We also provide some management recommendations for relevant industries.

A Bi-Level Optimization and Scheduling Strategy for Charging Stations Considering Battery Degradation

This paper proposes a bi-level optimization scheduling strategy for integrated photovoltaic (PV) and energy storage systems (ESS) to meet electric vehicle (EV) charging demands while reducing charging costs. First, a battery degradation cost model is developed in order to convert the long-term costs into short-term costs for real-time operation. The upper layer of ESS and power grid operation strategies are obtained by minimizing costs associated with battery degradation and distribution grid costs. The lower layer considers the PV uncertainty and the error caused by the upper layer operation strategy, and obtains the lower layer operation strategy by adding a penalty function to minimize fluctuations in power. Second, the author proposes a global optimization algorithm that combines Particle Swarm Optimization (PSO) and Sequential Quadratic Programming (SQP) in order to solve the above-mentioned models, effectively combining the global search feature of PSO with the local search capability of SQP. Finally, the bi-level optimization scheduling strategy is obtained by solving the model through the algorithm. Simulation results verify the practicality of the scheduling strategy and the effectiveness of the proposed algorithm.

A novel multi-level predictive management strategy to optimize phase-change energy storage and building-integrated renewable technologies operation under dynamic tariffs

In the evolving energy sector, where buildings are recognized as dynamic components of energy networks and smart grids, the implementation of new regulations and guidelines is crucial to optimize the interaction between buildings and the grid. The imperative to reduce building energy consumption facilitates the promotion of new technologies that rely on renewable energy generation and innovative materials. As technology has progressed, the multitude of energy vectors involved has made controlling energy systems increasingly challenging. This poses a barrier to the widespread adoption and implementation of cutting-edge technologies. In this framework, this paper explores an energy-efficient solution using an integrated photovoltaic/thermal collector and an active phase-change material storage system. The study optimizes the integration of technologies through a resistance capacitance model, assessing the impact on thermal comfort, energy savings and costs. A novel cascade methodology, combining particle swarm optimization search with model predictive control, is designed to select the optimal mode of operation for the proposed technologies. The economic feasibility of the proposed system is analyzed across different tariff structures, whereas the interaction with the grid is evaluated using energy flexibility key performance indicators. The energy and economic performance, as well as the flexibility of the system are assessed through a proof-of-concept conducted in an office building scenario. The results demonstrate an increase in energy efficiency, with savings ranging from 9% to 28% compared to a suitable baseline scenario, and a significant energy shift from on-peak to off-peak periods, potentially accounting for up to 46% of the total building load. This energy flexibility enables the grid to receive reduced demand during morning hours.

Short-term wind power prediction based on DWT-PSO-LSTM

With the “carbon peaking and carbon neutrality” target, quite a few people are focusing on the development of renewable energy, especially wind power, which is the largest source of renewable energy generation and is still expanding. In aiming to make the wind power forecasts more accurate by limiting the errors between the predicted and actual values, a model combining Particle Swarm Optimization, Discrete Wavelet Transform, and Long Short-Term Memory (DWT-PSO-LSTM) is developed to predict the wind power for short periods. First, the wind power is decomposed and normalized by DWT. Then, each decomposition result is input into LSTM prediction, and the model with the good result is obtained by finding the number of nodes and learning the efficiency of the best LSTM through PSO. Finally, the full prediction results are output and then all components are summed. Simulations using open wind power data from Yalova province, Turkey, indicate that the model advanced in this article can reduce the prediction errors better than other models.

Wind farm layout optimization through optimal wind turbine placement using a hybrid particle swarm optimization and genetic algorithm.

The placement and configuration of wind turbines (WTs) are the key factors in determining the performance and energy output of a wind farm (WF). This involves considering various elements such as wind speed, wind direction, and the interspacing between turbines in the design process. To achieve an optimized and consistent wind farm layout optimization (WFLO) for maximum output power, a novel hybrid algorithm hybrid particle swarm optimization and genetic algorithm (HPSOGA), combining particle swarm optimization (PSO) and genetic algorithm (GA), is proposed. HPSOGA can effectively handle problems with multiple local optima, as PSO explores multiple regions and GA refines solutions found by PSO. The framework has two phases, where PSO improves initial parameters in the first phase, and parameters are adjusted in the second phase for improved fitness. The wake effect is analyzed using the Jenson-Wake model, and the objective function considers the total cost of WTs and the power output of the WF. The interspacing of WTs is evaluated by the rule of thumb. HPSOGA outperforms other methods such as GA, BPSO-TVAC, L-SHADE, BRCGA, and EO-PS, producing better results in terms of total output power generation. The simulation results validate the reliability of HPSOGA in WFLO.

Plant Disease Image Segmentation applying the K-Means Algorithm, Firefly, and Particle Swarm Optimisation

Abstract: The process of dividing an image to several pieces with comparable features is known as segmentation of images. A difficult phase in the image segmentation process is to extract the information from the image. Clustering is used to segment photos of a similar type or to assess the relevance of data. In essence, clustering is an unsupervised learning process. The data elements that make up one cluster share the same kinds of characteristics. In other words, each cluster has a minimum difference between its points and a maximum difference from the data points of other clusters. The suggested approach clusters image pixels by combining Particle Swarm Optimization with K-Means. Since combined techniques produce the best results, Kmeans should be thanked. K-means combined with Particle Swarm Optimization performs better than firefly combined with Kmeans. The firefly algorithm is used to tackle optimization issues and has a variety of uses. The Firefly method has been utilized in numerous research and optimization fields. Firefly algorithm and Firefly have been effectively utilized to solve a variety of issues. The firefly algorithm needs to be altered or combined with other algorithms in order to be used to a wide range of problems. Due to their metaheuristic nature, contemporary algorithms are crucial for solving NP-Hard problems

Parameter Optimization and Control Strategy of Hybrid Electric Vehicle Transmission System based on Improved GA Algorithm

Most of the traditional hybrid electric vehicles (HEVs) choose to optimize the transmission ratio parameters, and the parameter changes of the whole vehicle and other components are only calculated as fixed values. It is difficult to give consideration to the optimization of the economy and power of hybrid vehicles. Therefore, the research proposes to build the transmission ratio, the required power of the vehicle’s working mode, and other models through the dynamic analysis. The parameters of the whole vehicle are optimized on the basis of parameter matching. At the same time, this paper chooses to adopt a hybrid optimization algorithm, combining particle swarm optimization (PSO) and genetic algorithm (GA). The weighted average method and constraint method are used to design the fitness function. The simulation experiment is carried out by Cruise software and MATLAB. Compare the iterative fitness of the PSO-GA algorithm with the traditional PSO and GA algorithm. It can be concluded that PSO-GA converges at the 12th iteration, with an average optimal fitness of 0.5239, which is higher than the traditional algorithm. At the same time, the parameter optimization of PSO-GA and the simulated annealing algorithm is compared. It is found that in the same task, the gasoline consumption after SA algorithm optimization is 0.561 L, while the fuel consumption under PSO-GA algorithm optimization is 0.475 L. The method proposed in this study has improved the power and economy of the HEV model and is effective.

Design of a novel hybrid soft computing model for passive components selection in multiple load Zeta converter topologies of solar PV energy system

Abstract This paper presents a new approach to improve the performance of Zeta converters, which are commonly used in cost-sensitive circuits to manage unregulated power supply. The converters are designed to produce positive output voltages based on input voltages, and they use a buck controller to power a PMOS-based FET for high-side control. Compared to other converters, such as SEPIC, Zeta converters are smaller and more scalable for micro applications due to the use of coupled inductor circuits. The performance of Zeta converters is heavily influenced by the ratings of their passive components. To optimize component rating choices, researchers have developed several pattern analysis models. However, these models often require context-specific ratings and lack a parameter selection method for continual reconfigurations, making them difficult to deploy in practice for different use cases. To address these limitations, the authors propose a hybrid soft computing methodology for passive component selection in multiple load Zeta converters. The proposed approach combines Particle Swarm Optimization (PSO) to determine initial component ratings and Grey Wolf Optimization (GWO) to improve conversion efficiency, output gain, and Total Harmonic Distortion (THD). This is achieved by modeling a fitness function that incorporates output metrics and optimizes them incrementally for real-time deployments. The results show that the suggested methodology can reduce THD by 6.5 %, increase conversion efficiency by 3.4 %, and maintain a gain improvement of 1.5 % across numerous use cases. These improvements make the model suitable for real-time use applications. Overall, the proposed approach provides a promising solution to the challenges of passive component selection in Zeta converters, which can lead to more efficient and cost-effective power management in various circuits.

RESEARCH ON NODE NETWORK TRANSMISSION CAPACITY PREDICTION MODEL FOR LARGE SCALE REMOTE SENSING DATA COLLECTION

Abstract. In recent years, the use of remote sensing technology has grown exponentially in various industries such as agriculture, forestry, and urban planning. Remote sensing data collection systems rely on a network of nodes to collect and transmit data. The transmission capacity of these node networks is a critical factor in the performance and efficiency of the entire system. However, accurately predicting the transmission capacity of a node network can be a challenging task. To carry out large scale open remote sensing data collection, it is necessary to predict the network transmission capacity of nodes in the face of the difference in the execution speed of each node for various tasks. It is necessary to predict the network transmission capacity of nodes. In this research, we propose a node network transmission capacity prediction model for large scale remote sensing data collection using a combination of Particle Swarm Optimization (PSO) and Backpropagation (BP) algorithms. The proposed PSO-BP model aims to accurately predict the transmission capacity of a node network in a remote sensing data collection system. The model is tested and evaluated using a large-scale dataset and the results show that the proposed model outperforms existing models in terms of prediction accuracy. This work contributes to the field of remote sensing data collection by providing a reliable and efficient method for predicting the transmission capacity of node networks.

Application of wrapper based hybrid system for classification of risk tolerance in the Indian mining industry

The degree to which an individual is willing to take risks i.e., risk tolerance is often cited as a significant causal element in the majority of workplace accidents. It is essential to determine the risk tolerance level of miners and utilise their risk profiles to design improved training modules, safety, recruitment, and deployment policies. This paper aims to identify the most critical factors (or features) influencing miners’ risk tolerance in the Indian coal industry and develop a robust prediction model to learn their risk tolerance levels. To do end, we first conducted a questionnaire survey representing the complete feature set (with 36 features) among 360 miners and divided their responses into five classes of risk tolerance. Next, we propose a wrapper based hybrid system that combines particle swarm optimization (PSO) and random forest (RF) to train a multi-class classifier with a subset of features. In general, the proposed system selects the best feature subset by iteratively generating different feature combinations using the PSO and training an RF classifier model to assess the effectiveness of the generated feature subsets for the F1-score. At last, we compared the PSO-RF with four traditional classification methods to evaluate its effectiveness in terms of precision, recall, F1-score, accuracy, goodness-of-fit, and area under the curve.