Roulette Method Research Articles

Research and application of short-term load forecasting based on CEEMDAN-LSTM modeling

Accurate short-term load forecasting plays a crucial role in guiding and regulating the operation of power companies. In this study, we propose a combined prediction model based on Long Short-Term Memory (LSTM) and Improved Whale Optimization Algorithm (IWOA) to enhance prediction accuracy and address the limitations of existing single methods. The parameter optimization of the LSTM model requires significant computing resources and time. To tackle this issue, we introduced the Whale Optimization Algorithm (WOA) and improved the algorithm through the roulette method to form a whale optimization algorithm that enhances its global search capability and avoids falling into local optimal solutions. Additionally, in order to handle the nonlinearity and non-smoothness of the input data of the model, we utilized fully integrated Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) in this study to improve the efficiency of model training. By combining these techniques, we constructed a new CEEMDAN-IWOA-LSTM combined prediction model. The simulation results in MATLAB demonstrate that the prediction accuracy of this model reaches 99.05 %, which surpasses other prediction models in all evaluation indexes.

Optimization of engineering parameters of deflagration fracturing in shale reservoirs based on hybrid proxy model

Engineering parameter optimization of deflagration fracturing in shale reservoirs is operated with single factor analysis and orthogonal experimental design analysis. There are problems of the difficulty to search the global optimal solution, time-consuming optimization and low computation efficiency. To resolve these problems, a method of optimizing engineering parameters of deflagration fracturing based on the hybrid proxy model was proposed in this paper. The parameters with significant effects on deflagration fracturing were selected as variables, and the models for prediction of reservoir burst degree and stimulated area were established based on Radial Basis Function model, Kriging interpolation model and eXtreme Gradient Boosting regression model respectively. A hybrid proxy model based on the roulette method was established by integrating the priorities of these three models. Then, a multi-objective optimization method of deflagration fracturing based on the hybrid proxy model and was established by integrating the Nondominated Sorting Genetic algorithm II with the engineering parameters as variables and the maximum stimulated area and minimum burst degree as objectives. Optimal design of the deflagration fracturing scheme was achieved. The results show that the hybrid proxy model can accurately predict the evaluation index of the fracturing results in vertical and horizontal wells, and the prediction accuracy is maintained at about 0.9. At the same time, compared with numerical model, the proposed method greatly saves the calculation time. The method proposed by this paper provides the solution to the problem of multi-objective optimization of deflagration fracturing engineering parameters, weighs the reservoir failure degree and the stimulation range, and provides guidance for field operation.

An effective multi-objective bald eagle search algorithm for solving engineering design problems

In this paper, a multi-objective bald eagle search algorithm (MOBES) is proposed. The MOBES introduces an archive mechanism to store the non-dominated solutions obtained by the algorithm. When the archive overflows, remove the most crowded solutions by using the roulette method. The MOBES also adds elite selection strategy to guide other individuals to optimize by selecting elite individuals in the population. The efficiency of MOBES is validated on CEC 2020 benchmark functions, and the results demonstrate that the proposed algorithm is more efficient than its competitors in terms of convergence, diversity and distribution of solutions. The MOBES is also applied to two-objective, tri-objective and four-objective engineering design problems in real world. The results show its superiority in handling challenging multi-objective optimization problems with unknown true Pareto optimal solutions and fronts, and it is more competitive than other algorithms.

Multi-Drone Optimal Mission Assignment and 3D Path Planning for Disaster Rescue

In a three-dimensional (3D) disaster rescue mission environment, multi-drone mission assignments and path planning are challenging. Aiming at this problem, a mission assignment method based on adaptive genetic algorithms (AGA) and a path planning method using sine–cosine particle swarm optimization (SCPSO) are proposed. First, an original 3D digital terrain model is constructed. Second, common threat sources in disaster rescue environments are modeled, including mountains, transmission towers, and severe weather. Third, a cost–revenue function that considers factors such as drone performance, demand for mission points, elevation cost, and threat sources, is formulated to assign missions to multiple drones. Fourth, an AGA is employed to realize the multi-drone mission assignment. To enhance convergence speed and optimize performance in finding the optimal solution, an AGA using both the roulette method and the elite retention method is proposed. Additionally, the parameters of the AGA are adjusted according to the changes in the fitness function. Furthermore, the improved circle algorithm is also used to preprocess the mission sequence for AGA. Finally, based on the sine–cosine function model, a SCPSO is proposed for planning the optimal flight path between adjacent task points. In addition, the inertia and acceleration coefficients of linear weights are designed for SCPSO so as to enhance its performance to escape the local minimum, explore the search space more thoroughly, and achieve the purpose of global optimization. A multitude of simulation experiments have demonstrated the validity of our method.

Analysis of relative error in perturbation Monte Carlo simulations of radiative transport.

Perturbation and differential Monte Carlo (pMC/dMC) methods, used in conjunction with nonlinear optimization methods, have been successfully applied to solve inverse problems in diffuse optics. Application of pMC to systems over a large range of optical properties requires optimal "placement" of baseline conventional Monte Carlo (cMC) simulations to minimize the pMC variance. The inability to predict the growth in pMC solution uncertainty with perturbation size limits the application of pMC, especially for multispectral datasets where the variation of optical properties can be substantial. We aim to predict the variation of pMC variance with perturbation size without explicit computation of perturbed photon weights. Our proposed method can be used to determine the range of optical properties over which pMC predictions provide sufficient accuracy. This method can be used to specify the optical properties for the reference cMC simulations that pMC utilizes to provide accurate predictions over a desired optical property range. We utilize a conventional error propagation methodology to calculate changes in pMC relative error for Monte Carlo simulations. We demonstrate this methodology for spatially resolved diffuse reflectance measurements with ±20% scattering perturbations. We examine the performance of our method for reference simulations spanning a broad range of optical properties relevant for diffuse optical imaging of biological tissues. Our predictions are computed using the variance, covariance, and skewness of the photon weight, path length, and collision distributions generated by the reference simulation. We find that our methodology performs best when used in conjunction with reference cMC simulations that utilize Russian Roulette (RR) method. Specifically, we demonstrate that for a proximal detector placed immediately adjacent to the source, we can estimate the pMC relative error within 5% of the true value for scattering perturbations in the range of . For a distal detector placed at transport mean free paths relative to the source, our method provides relative error estimates within 20% for scattering perturbations in the range of . Moreover, reference simulations performed at lower values showed better performance for both proximal and distal detectors. These findings indicate that reference simulations utilizing continuous absorption weighting (CAW) with the Russian Roulette method and executed using optical properties with a low ratio spanning the desired range of values, are highly advantageous for the deployment of pMC to obtain radiative transport estimates over a wide range of optical properties.

A 3D Offline Packing Algorithm considering Cargo Orientation and Stability

The box packing problem can be generalized as placing a batch of cargos with a specified number of different physical characteristics into a specified box. Suppose that a batch of cuboid cargos of different sizes are to be loaded into a batch of boxes of the same type, the cargos have constraints such as orientation and stability. Taking the mean value of the reciprocal of space utilization as the objective function, this paper designs a hybrid genetic algorithm that combines genetic algorithm and tabu search algorithm. Aiming at the information of the packing sequence and the rotating state of the box in the packing scheme, a two-stage real number encoding method and decoding method based on random keys are designed, and a crossover operation based on partial random keys and uniform crossover is designed. In order to convert the solution searched by the optimization algorithm into the actual packing scheme, a heuristic loading algorithm is designed while using the positioning rule of the lower left corner, the space selection rule of the minimum space, and the division and merging rules of the remaining space. In the early stage, the roulette method was used to strengthen the global search ability, and in the later stage, the optimal preservation strategy was used to speed up the algorithm convergence. To make up for the shortcomings of the genetic algorithm’s weak local search ability and slow convergence speed, the tabu search algorithm was used as a mutation operation in the genetic algorithm. The solution in the generation is used as the initial solution of the tabu search algorithm, and the search process is carried out. Finally, this paper tests the proposed hybrid algorithm on 6 groups of weakly heterogeneous and strongly heterogeneous data in the BR dataset. The results prove that the proposed algorithm can reduce the usage of boxes.

A variable neighborhood search-based algorithm with adaptive local search for the Vehicle Routing Problem with Time Windows and multi-depots aiming for vehicle fleet reduction

This article addresses the Multi-Depot Vehicle Routing Problem with Time Windows with the minimization of the number of used vehicles, denominated as MDVRPTW*. This problem is a variant of the classical MDVRPTW, which only minimizes the total traveled distance. We developed an algorithm named Smart General Variable Neighborhood Search with Adaptive Local Search (SGVNSALS) to solve this problem, and, for comparison purposes, we also implemented a Smart General Variable Neighborhood Search (SGVNS) and a General Variable Neighborhood Search (GVNS) algorithms. The SGVNSALS algorithm alternates the local search engine between two different strategies. In the first strategy, the Randomized Variable Neighborhood Descent method (RVND) performs the local search, and, when applying this strategy, most successful neighborhoods receive a higher score. In the second strategy, the local search method is applied only in a single neighborhood, chosen by a roulette method. Thus, the application of the first local search strategy serves as a learning method for applying the second strategy. To test these algorithms, we use benchmark instances from MDVRPTW involving up to 960 customers, 12 depots, and 120 vehicles. The results show SGVNSALS performance surpassed both SGVNS and GVNS concerning the number of used vehicles and covered distance. As there are no algorithms in the literature dealing with MDVRPTW*, we compared the results from SGVNSALS with those of the best-known solutions concerning these instances for MDVRPTW, where the objective is only to minimize the total distance covered. The results showed that the proposed algorithm reduced the vehicle fleet by 91.18% of the evaluated instances, and the fleet size achieved an average reduction of up to 23.32%. However, there was an average increase of up to 31.48% in total distance traveled in these instances. Finally, the article evaluated the contribution of each neighborhood to the local search and shaking operations of the algorithm, allowing the identification of the neighborhoods that most contribute to a better exploration of the solution space of the problem.

Optimization analysis of energy storage application based on electricity price arbitrage and ancillary services

Energy storage is an effective way to facilitate renewable energy (RE) development. Its technical performance and economic performance are key factors for large scale applications. As battery energy storage system (BESS) is one commercially-developed energy storage technology at present, BESS is utilized to connect to RE generation. BESS couple with RE can balance the generation and load, and provide auxiliary services. Thus, the technical and economic performance of this coupling system was investigated. The coupling system generates extra revenue compared to RE-only through arbitrage considering peak-valley electricity price and ancillary services. In order to maximize the net revenues of BESS, a multi-objective three-level model for the optimal configuration of BESS was developed. The outer layer was a model for the optimal configuration of BESS, the middle layer was a multi-objective optimal model for BESS to participate in electricity price arbitrage and reserve ancillary services, and the inner layer was an optimal scheduling model that coordinated wind power, photovoltaic (PV) power and BESS. The multi-objective genetic algorithm (GA) based on the roulette method was employed to solve the optimal model. A case study was conducted, and the annual net revenues of BESS under different BESS capacities were evaluated. When the annual net revenues of BESS reach the maximum, the optimal BESS capacity is obtained. Sensitive analysis was also conducted considering different price difference, environment conditions of irradiance, wind speed. The effective trend and optimization values were calculated. The study presented a solution including methodology and values for how to determine the installation of energy storage to RE.

Clearing-based multimodal multi-objective evolutionary optimization with layer-to-layer strategy

Equivalent Pareto sets and local Pareto sets in decision space are involved in multimodal multi-objective optimization problems (MMOPs). While popular multimodal multi-objective evolutionary algorithms (MMEAs) devote greater attention to locating equivalent Pareto sets in decision space, resulting in the fact that local Pareto sets are overlooked. To tackle this issue, a clearing-based evolutionary algorithm with layer-to-layer evolution strategy (CEA-LES) is therefore proposed in this paper. A clearing-based niching technique is used in CEA-LES to remove inferior local Pareto optimal solutions, in which the clearing radius dynamically changes with the number of nearest neighbors of each individual. To develop equivalent global Pareto sets and local Pareto sets, a layer-to-layer evolutionary strategy is proposed based on Pareto ranking. Each layer performs mutation selection and reproduction operations with the aid of its closest neighbor layer to produce offspring. Particularly, the whole evolutionary operation is divided into two stages, and the first stage is to select parents using the roulette method and the second stage is using the tournament method. An environmental selection strategy is suggested to maintain diverse solutions and balance the distribution of solutions. The proposed algorithm is performed on CEC 2020 MMOPs benchmark with local Pareto set and Polygon-based MMOPs and is compared with some state-of-the-art MMEAs. Experimental results demonstrate that the proposed algorithm obtains superior performance in comparison to its competing algorithms, and is capable of locating equivalent global Pareto sets and local Pareto sets, simultaneously.

Bi-level planning method of urban electric vehicle charging station considering multiple demand scenarios and multi-type charging piles

The planning of electric vehicle (EV) charging stations with a comprehensive consideration of the multi-type charging demands and the acceptance capacities of the distribution network is of great significance to the development of EVs and the transformation of the distribution network. At present, most studies determine EV charging needs based on user travel paths, but they have not taken the behavior uncertainty of EV owners and the diversity of their demands into account. The probability statistics on the massive data of EV travels can help excavating the travel and charging rules of the EVs. Based on user travel data, the Markov chain and the roulette method are used to simulates EV charging requirements in three scenarios considering various uncertain factors, and then a K-means clustering algorithm is used to obtain charging requirements in three scenarios. On this basis, a bi-level planning model of charging station with maximum annual profit of construction and operation and minimum comprehensive charging cost of EVs as multi-objective function is proposed. This model also considers many constraints, such as cooperative service of multi-type charging piles, acceptance capacity of distribution network and so on. The upper model takes the location and capacity of charging station planning as control variables. The lower model was established to minimize the comprehensive charging cost of EVs. The upper and lower models interact and couple with each other. The solution process of bi-level planning model was designed through using firefly algorithm. Finally, taking the urban area of a city in China as the planning area, and the transportation network coupled with the IEEE 69 node distribution network as an example, the validity and correctness of the proposed model are verified.

Enhanced ant colony algorithm with communication mechanism for mobile robot path planning

In mobile robot path planning, the ant colony algorithm has the problem that the historical paths explored by ants cannot be fully utilized. With this in mind, in this paper an enhanced ant colony algorithm with a communication mechanism is proposed. The communication mechanism is inspired by the contact of ant tentacles in nature, which can integrate historical paths to obtain a better composite path. To further improve the algorithm, an enlarged roulette method is presented to accelerate the convergence. Subsequently, an adaptive sigmoid attenuation function is designed to optimize the heuristic information at different stages. The various forms of the deadlock problem are analyzed and specific strategies formulated. Finally, parameter determination and comparison experiments are carried out. The experimental results demonstrate the efficiency of the proposed method and its considerable advantages in enhancing the performance of the ant colony algorithm.

Research on Design and Dispatching of Circular Shuttle System

The shuttle is also called Rail Guide Vehicle (RGV). It has the characteristics of fast conveying speed, good flexibility, and high degree of automation. The circular RGV system is widely used in logistics network dispatching. The genetic operator of the ordinary partheno genetic algorithm is improved by the single-point transposition operator and the roulette method, and the improved partheno genetic algorithm is obtained. The improved partheno genetic algorithm is used to model and design the circular shuttle system.

Using Non-dominated Sorting Particle Swarm Optimization Algorithm II for Bi-objective Flow Shop Scheduling Problems

A hybrid particulate swarm optimization (hybrid) combination of an optimization algorithm of the particle swarm and a variable neighborhood search algorithm is proposed for the multi-objective permutation flow shop scheduling problem (PFSP) with the smallest cumulative completion time and the smallest total flow time. Algorithm for hybrid particulate swarm optimization (HPSO) is applied to maintain a fair combination of centralized search with decentralized search. The Nawaz-Enscore-Ham )NEH) heuristic algorithm in this hybrid algorithm is used to initialize populations in order to improve the efficiency of the initial solution. The method design is based on ascending order (ranked-order-value, ROV), applying the continuous PSO algorithm to the PFSP, introducing the external archive set storage Pareto solution, and using a hybrid strategy that combines strong dominance and aggregation distance to ensure the distribution of the solution set. We adopted the Sigma method and the roulette method, based on the aggregation distance, to select the global optimal solution. A variable neighborhood search algorithm was proposed to further search the Pareto solution in the external set. The suggested hybrid algorithm was used to solve the Taillard test set and equate the test results with the SPEA2 algorithm to check the scheduling algorithm’s efficacy.

Study on the friction resistance calculation method of a flexible shaft of wire rope based on genetic algorithm

This study aims to finding out the calculation formula of friction resistance of steel wire's flexible shaft in bending push-pull state. The operation principle is based on the adhesive friction theory and Newton's classical friction formula. The friction force f is measured by experiment under the conditions of same length L, different diameter D and different curvature K, and the curve trajectory equation is obtained by curve fitting with mathematical tools. Then, according to the experimental data, the greater the curvature of flexible shaft is (that's, the smaller the bending radius is), the greater the positive pressure between shaft core and the sheath will be. The positive pressure N between the shaft core and the sheath is equal to the curvature K direct ratio. Therefore, it can be concluded that the positive pressure N of the shaft core and sheath is proportional to the curvature K, and the proportional coefficient β is introduced. The experimental results show that the functional relationship between the friction force F and the curvature K of the flexible shaft can be derived, the diameter D and curvature K of the mandrel have a great influence on the friction resistance of the flexible shaft, that is, the empirical friction resistance formula. In order to reduce the relative error and improve the accuracy of the formula. By combining elite retention strategy with roulette method and replacing the current worst genetic algorithm with historical optimum, the parameter β in the formula is optimized. After optimization, the calculation formula of friction resistance of four flexible shafts of steel wire under bending push-pull state is obtained. The author's pioneer work has contributed to the calculation of friction resistance under bending push-pull, and the average calculation error is 5%, which meets the requirements of calculation accuracy.

A feedback-based prediction strategy for dynamic multi-objective evolutionary optimization

Prediction methods are widely used to solve dynamic multi-objective optimization problems (DMOPs). The key to the success of prediction methods lies in the accurate tracking of the new location of the Pareto set (PS) or Pareto front (PF) in a new environment. To improve the prediction accuracy, this paper proposes a novel feedback-based prediction strategy (FPS), which consists of two feedback mechanisms, namely correction feedback (CF) and effectiveness feedback (EF). CF is used to correct an initial prediction model. When the environment changes, CF constructs a representative individual to reflect the characteristics of the current population. The predicted solution of this individual in the new environment is calculated based on the initial prediction model. Afterward, a step size exploration method based on variable classification is introduced to adaptively correct the prediction model. EF is applied to enhance the effectiveness of re-initialization in two stages. In the first stage, half of the individuals in the population are re-initialized based on the corrected prediction model. In the second stage, EF re-initializes the rest of the individuals in the population using two rounds of roulette method based on the re-initialization effectiveness feedback of the first stage. The proposed FPS is incorporated into a dynamic multi-objective optimization evolutionary algorithm (DMOEA) based on decomposition resulting in a new algorithm denoted as MOEA/D-FPS. MOEA/D-FPS is compared with six state-of-the-art DMOEAs on twenty-two different benchmark problems. The experimental results demonstrate the effectiveness and efficacy of MOEA/D-FPS in solving DMOPs.

Steel logistics park layout based on market basket analysis and accessibility

In this study, we used market basket analysis and land accessibility for the layout of MG Steel Logistics Park. Due to the unreasonable cargo space layout, the outbound trucks in the MG Steel Logistics Park detour and transfer, which caused congestion. Using market basket analysis, this research took outbound trucks as the research object to measure the degree of correlation between cargo locations. Then, we measured the convenience of cargo locations by the accessibility and matched it with the steel outbound frequency. We established a model and got the layout allocation plan with the maximum degree of relevance and the minimum difference in cargo-location matching as the target. In the solution algorithm, we use roulette method and the elite retention strategy to improve the genetic algorithm. Finally, we compared the results before and after optimization. We found that the number of truck transfers was reduced by 33%, and the truck staying time was reduced by 21%.

Research on Logistics Distribution Vehicle Scheduling Based on Heuristic Genetic Algorithm

To study the genetic algorithm, this paper solves the problem of shop scheduling under the premise of layout Flying − V. Firstly, double‐layer coding is used for optimization. When calculating fitness, the time to return to the mouth P&D approaches the optimum through the greedy idea. Individual screening is carried out through the roulette method. Different crossover and genetic operators are used for different coding layers. Through thinking of elitism and catastrophe and the immigration operator to ensure the diversity of the algorithm in the calculation process, it can achieve the recommendation of the number of cars to control the cost. The stability of the algorithm is good. It can recommend a better picking sequence and number of carts for various types of picking problems.

PRO111 Using Expert Judgement to Inform Decision Making WHEN the Evidence Base Is Limited: A Case Study in Haemophilia

Benefits associated with physical activity (PA) for people with haemophilia (PWH) may include improvements in joint, bone and muscle health. However, the factor VIII activity level required to avoid a bleeding episode with PA is unknown. We therefore sought to determine if clinically acceptable estimates could be generated using a modified version of the Sheffield Elicitation Framework (SHELF), a formal approach for eliciting judgements regarding probability distributions. A panel of 9 haemophilia experts which included five consultant haemotologists, two clinical specialist physiotherapists, one haemophilia nurse consultant and one patient advocate participated. Based on the 2017 National Hemophilia Foundation (NHF) PA descriptions, clinical experts estimated factor levels at which a bleed could be avoided. The estimates were elicited using an adapted version of the SHELF Roulette method. Probability distributions for each scenario were combined and presented to the panel of experts. All responses were judged to be correct applications of the SHELF method and estimates were combined. The final set of outcomes and approach were accepted by the panel and may be used to inform future research and evaluation for factor VIII activity level required to avoid a bleeding episode with PA. Important health care decisions are required often where the evidence base is limited. SHELF is a formal approach for harnessing expert judgements. SHELF can be used to promote evidence-based practice by use of a methodological tool to facilitate the combination of expert judgement to guide health care decisions.

A New Type of Evolutionary Strategy Based on a Multi-player Iterated Prisoner’s Dilemma Game

AbstractAccording to the philosophy of self-cultivation that “one should refine his personal virtue when in poverty, and help save the world when in success”, a new type of evolutionary strategy, Poor-Competition-Rich-Cooperation (PCRC), is proposed. To discuss its superiority and inferiority, based on a multi-player iterated Prisoner’s Dilemma game, PCRC and other six kinds of strategies are played by using the roulette method in three different populations (a uniformly distributed population, a cooperation-preference population, a defection-preference population). The payoff characteristics for each strategy under different temptation coefficients and noise values are also analyzed. Simulation results indicate that PCRC has a sufficient robustness and its payoff presents a basically monotonic increasing tendency with the increment of noise. The superiority of PCRC becomes more obvious when the temptation coefficient becomes larger. Furthermore, a higher population preference for defection yields a more obvious advantage for PCRC.

Expert elicitation of the diagnostic performance of two tests for Bacterial Kidney Disease (BKD) surveillance in Atlantic salmon (Salmo salar L.) broodstock in Chile

The objective of this study was to obtain diagnostic performance estimates for immunofluorescence antibody test (IFAT) and quantitative polymerase chain reaction (qPCR) tests, for Bacterial Kidney Disease (BKD) surveillance in farmed Atlantic salmon (Salmo salar.) broodstock without clinical signs compatible with the disease in Chile. To obtain diagnostic sensitivity (DSe) and specificity (DSp) estimates of those tests, an expert elicitation process was conducted using the trial roulette method during a workshop with 18 national experts on BKD diagnostics and control. A questionnaire was given to the experts to gather information on their previous experience with BKD, and 12 experts who received an introduction to the expert-elicitation process and graphical representation of statistical distributions. Experts were divided into three groups and requested to draw distributions of DSe and DSp parameters using an online tool. Then figures where projected and discussed among participants. After the discussion round, experts were requested to redraw their distributions (if considered necessary). The agreement between groups was assessed by calculating the overlapping areas between the three distributions for each parameter. Finally, a consensus distribution was generated.In general, groups had moderate to high agreement with overlapping areas between 53% to 93% for DSpIFAT, DSeqPCR, and DSpqPCR. Conversely, no agreement was reached for the DSeIFAT distribution. Specifically, median estimates of 89.5%, 90.5%, and 95.9%, were obtained for DSpIFAT, DSeqPCR, &DSpqPCR, respectively. In the case of DSeIFAT, the first group provided a median estimate of 28%, whereas groups 2 and 3 reached a consensus value of approximately 62%. This study provides information that is not available in the country, and will help to adjust current BKD control programs, which mainly rely on the use of qPCR assays.