Average Improvement Rate Research Articles

An improved Kepler optimization algorithm for module parameter identification supporting PV power estimation

Identification of photovoltaic (PV) module characteristics in solar systems is a vital task, nowadays, for optimal PV power estimation. In this paper, this challenge task has been studied using a novel advanced Kepler optimization algorithm (KOA). The standard version of KOA is adopted and assessed for getting the nine parameters of the PV triple diode model (3DM) considering three different practical PV modules. Kepler's principles of planetary motion are used by KOA to forecast the location and velocity of planets at any particular moment. However, the success rate of the KOA is not compatible, and its efficiency needs to be enhanced. As a result, an Improved KOA (IKOA) is created by incorporating an advanced mechanism of Local Escaping Operator (LEO), resulting in improved process of searching with evading local optima. This mechanism means that the exploitation approach will activate with around half of the solutions for every iteration starting at the initial phase of the iteration journey. The suggested IKOA besides the standard KOA are developed for predicting PV parameters for three distinct PV modules which are Photowatt PWP201, R.T.C France and STM6-40/36. The results corresponding to the latest algorithms are also compared with the proposed IKOA about different published works. The simulation findings reveal that the suggested IKOA exhibits notable average improvement rates for the three modules of 62.27 %, 55.1 %, and 32.12 %, respectively. Furthermore, the suggested IKOA asserts significant superiority and robustness over previously reported results.

A framework of integrated differential evolution variants based on adaptive relay mode for global optimization

Differential evolution (DE) is highly competitive in single-objective real parameter optimization. However, there are still some problems with differential evolutionary variants in optimizing complex multimode functions, such as poor solution accuracy and slow convergence. To address these problems, an optimization framework of integrated DE variants based on adaptive relay mode (fDE-ARM) is proposed. In this framework, different DE variants are integrated through two adaptive relay mechanisms to give full play to the advantages of the algorithms, thereby improving the performance of the whole algorithm. For the first adaptive relay mode, when the currently executed algorithm is judged to have converged, the population is updated by Gaussian random walk, and then the optimization is continued through the relay algorithm. For the second adaptive relay mode, the relay condition is determined by the average fitness improvement rate. If the condition is met, the relay algorithm takes over the optimization. At the same time, if the diversity is lower than the threshold, to improve the exploration, the roulette wheel method is used to select some individuals to perform the Gaussian random walk. In addition, a feedback mechanism is introduced in the relay process to avoid false switching. To verify the performance of the proposed algorithm, extensive simulations are performed on CEC2005, CEC2014, CEC2017, and CEC2021 benchmark functions. In addition, three engineering problems are used to test the performance. Compared with some newly proposed optimization algorithms, fDE-ARM is statistically superior to the comparison algorithms in terms of solution accuracy, convergence speed, and stability.

Method of generating potential evapotranspiration with high precision and resolution

Potential evapotranspiration (PET) is a key factor in hydrological cycle and energy balance and plays an important role in drought and global climate change response. Existing observational and modeling methods for PET retrieval have their limitations, such as low precision and poor spatial resolution, which becomes the focus of this study. A hybrid PET fusion (HPF) method is proposed by fusing station- and grid-based PET, in which the PET expression is determined by considering the factors of location, temperature, and zenith total delay (ZTD). In addition, an improved Helmert variance component estimation method is introduced to determine the optimal weights of the HPF model. Corresponding data, which include monthly Thornthwaite (TH)-derived PET data with a spatial resolution of 0.25° × 0.25° and Penman–Monteith (PM)-derived PET data at 704 meteorological stations, over the past 60 years from 1959 to 2018 in China are selected. The 10-fold cross-validation method is introduced to evaluate the internal and external accuracies of the proposed HPF method. Statistical result shows that the average root mean square (RMS) of the proposed HPF method is 13.98 mm, with an average RMS improvement rate (IR) of 46.71 % compared with TH-derived PET, when PM-derived PET is regarded as a reference. Moreover, the performance of the HPF-derived standardized precipitation evapotranspiration index (SPEI) is evaluated at different time scales, and the average RMS is 0.3, with an average RMS IR of 26.33 % compared with TH-derived SPEI. Such results verify the good performance of the proposed HPF model and enrich the methods for obtaining PET with high precision and resolution.

Estimating water quality parameters of freshwater aquaculture ponds using UAV-based multispectral images

UAV imaging technology has become one of the means to quickly monitor water quality parameters in freshwater aquaculture ponds. The change of sunlight during a long flight affects the quality of UAV images, which will reduce the accuracy of monitoring water quality. This study aims to propose a method to correct spectral variation during UAV imaging and apply it to detect dissolved organic matter (DOM) concentration and dissolved oxygen (DO) content in freshwater aquaculture ponds. Firstly, a spectral correction method was used to transform UAV-based multispectral images. The spectral data before and after correction was extracted. Secondly, 18 spectral indices before and after correction were constructed. The optimal combination of indices was identified using correlation analysis algorithm. The estimation models of water quality parameters were then constructed and compared using the Random Forest (RF), Support Vector Regression (SVR), and BP neural network (BP) methods. The results showed that the accuracy of estimating DOM concentration using corrected spectral indices was significantly improved compared to pre-correction models, with the highest improvement of 38 % (SVR), the lowest of 23 % (BP), and an average improvement of 31 %. The RF model performed best, achieving R² = 0.81, RMSE = 3.34 mg/L, and MAE = 2.17 mg/L. For DO content estimation, the accuracy of models using corrected spectral indices was also improved significantly, with the highest improvement of 97 % (RF), the lowest of 39 % (SVR), and an average improvement rate of 67 %. The Random Forest model was again optimal, with R² = 0.69, RMSE = 1.97 mg/L, and MAE = 1.47 mg/L. This study indicates that the proposed spectral correction method helps to map the concentration of DOM and DO in freshwater aquaculture ponds with high accuracy using UAV-based multispectral images.

Enhancing Numeracy Skills in Elementary Students through the Traditional Congklak Game: A Study in Kudus

The objective of this study is to assess the efficacy of the conventional congklak game in enhancing numeracy abilities among primary school pupils in Kudus. The capacity to enumerate is a fundamental skill in the field of mathematics education, which is sometimes regarded as tedious by young learners. This study employed an experimental research approach and included a sample of 100 students representing diverse social and economic backgrounds. The employed methodologies encompass literature review, documentation, direct observation, and pre-test and post-test assessments to evaluate students' numeracy abilities. In addition, questionnaires and interviews were used to analyse several dimensions like learning motivation, social interaction, and family environmental support. The findings indicated that pupils who were taught utilizing the congklak game shown a notable enhancement in their numeracy abilities in comparison to students who employed traditional approaches, with an average rate of improvement of 28%. Furthermore, the congklak game has been empirically shown to enhance both learning motivation and social interaction among students. The findings of this study validate the need of including conventional games within the primary education curriculum in order to establish a learning environment that is both entertaining and efficient. Therefore, this study provides a substantial contribution to the advancement of novel and efficient learning methodologies. The findings from this study can serve as a valuable resource for policy makers and educators in developing a curriculum that is both engaging and effective in enhancing students' fundamental skills.

The role of tsui scale in the treatment of primary cervical dystonia

Objective: To evaluate the severity of patients with primary cervical dystonia and the effectiveness of treatment with botulinum toxin A (Dysport based on the Tsui scale Methods: We conducted a cross-sectional descriptive study of all patients with primary cervical dystonia treated with botulinum toxin A injections at Tam Anh General Hospital from November 2022 to April 2024. Patients were assessed in detail on the Tsui scale before and after treatment 4-6 weeks. Patients were considered to have improvement when the Tsui score after treatment decreased by at least 30% compared to before treatment. Results: There were 17 patients (12 men and 5 women) who met the criteria in our study. The Tsui score before treatment in the male patient group, complex disease, with tremor was higher than that in the female patient group, simple disease, without tremor (p< 0.001). 100% of patients responded to treatment with an average improvement rate of 0.56. The Tsui score after 4-6 weeks of injection (4.59 ± 2.87) improved significantly compared to before treatment (9.71 ± 4.34) (p< 0.001). Conclusion: Our research has demonstrated an enhancement in Tsui score following treatment with BoNT among patients with cervical dystonia. The Tsui score is an objective measure for evaluating treatment effectiveness and should be more widely used in clinical practice.

Predicting the potential of middle- and long-distance track runners by evaluating the performance improvement rate.

The aim of this study was twofold: 1) to determine the rate of performance improvement among France's top 10 athletes in middle- and long-distance events (e.g., 800 m, 1500 m and 5000 m) by analyzing their personal best performances per season over several years; and 2) to develop an index of the optimal performance improvement rate for use by elite coaches and athletes in assessing athletes' progression, predicting potential performances, and possibly detecting high-potential athletes. The top 10 athletes in the Fédération Française d'Athlétisme (FFA) rankings of the 800-m, 1500-m and 5000-m events for each sex were assessed for their history of race times before achieving their best race time (BRT). For each athlete, the difference between the current BRT and last season's BRT was defined as the 1-season improvement rate (1-SIR), whereas the average improvement rate in the last and preceding seasons was the multiseason improvement rate (M-SIR). Sex differences were observed in the 5000 m only for M-SIR (%) (P<0.05), and significantly higher rates of improvement were observed for 1-SIR (min) and M-SIR mostly for the 5000 m as opposed to the 800 m and 1500 m. Prediction using this index may be used to detect talents (those who have the potential for high level performances and/or the potential to break national records) and to follow and optimize training strategy and competitions.

Intensive Care Management of Severe Hyponatraemia-An Observational Study.

Background and Subject: Hyponatraemia is a common electrolyte disorder. For patients with severe hyponatraemia, intensive care unit (ICU) admission may be required. This will enable close monitoring and allow safe management of sodium levels effectively. While severe hyponatraemia may be associated with significant symptoms, rapid overcorrection of hyponatraemia can lead to complications. We aimed to describe the management and outcomes of severe hyponatraemia in our ICU and identify risk factors for overcorrection. Materials and Methods: This was a retrospective single-centre cohort that included consecutive adults admitted to the ICU with serum sodium < 120 mmol/L between 1 January 2017 and 8 March 2023. Anonymised data were collected from electronic records. We included 181 patients (median age 67 years, 51% male). Results: Median admission serum sodium was 113 mmol/L (IQR: 108-117), with an average rate of improvement over the first 48 h of 10 mmol/L/day (IQR: 5-15 mmol/L). A total of 62 patients (34%) met the criteria for overcorrection at 48 h, and they were younger, presented with severe symptoms (seizures/arrythmias), and had lower admission sodium concentration. They were more likely to be treated with hypertonic saline infusions. Lower admission sodium was an independent risk factor for overcorrection within 48 h, whereas the presence of liver cirrhosis and fluid restriction was associated with normal correction. No difference was identified between the normal and overcorrected cohorts for ICU/hospital length of stay or mortality. Conclusions: In some patients with severe hyponatraemia, overcorrection is inevitable to avoid symptoms such as seizures and arrhythmias, and consequently, we highlight the key factors associated with overcorrection. Overall, we identified that overcorrection was common and concordant with the current literature.

A Fractional Order-Kepler Optimization Algorithm (FO-KOA) for single and double-diode parameters PV cell extraction

The primary objective of this study is to investigate the effects of the Fractional Order Kepler Optimization Algorithm (FO-KOA) on photovoltaic (PV) module feature identification in solar systems. Leveraging the strengths of the original KOA, FO-KOA introduces fractional order elements and a Local Escaping Approach (LEA) to enhance search efficiency and prevent premature convergence. The FO element provides effective information and past expertise sharing amongst the participants to avoid premature converging. Additionally, LEA is incorporated to boost the search procedure by evading local optimization. The single-diode-model (SDM) and Double-diode-model (DDM) are two different equivalent circuits that are used for obtaining the unidentified parameters of the PV. Applied to KC-200, Ultra-Power-85, and SP-70 PV modules, FO-KOA is compared to the original KOA technique and contemporary algorithms. Simulation results demonstrate FO-KOA's remarkable average improvement rates, showcasing its significant advantages and robustness over earlier reported methods. The proposed FO-KOA demonstrates exceptional performance, outperforming existing algorithms by 94.42 %–99.73 % in optimizing PV cell parameter extraction, particularly for the KC200GT module, showcasing consistent superiority and robustness. Also, the proposed FO-KOA is validated of on SDM and DDM for the well-known RTC France PV cell.

Out-of-order execution enabled deep reinforcement learning for dynamic additive manufacturing scheduling

Additive Manufacturing (AM) has revolutionized the production landscape by enabling on-demand customized manufacturing. However, the efficient management of dynamic AM orders poses significant challenges for production planning and scheduling. This paper addresses the dynamic scheduling problem considering batch processing, random order arrival and machine eligibility constraints, aiming to minimize total tardiness in a parallel non-identical AM machine environment. To tackle this problem, we propose the out-of-order enabled dueling deep Q network (O3-DDQN) approach. In the proposed approach, the problem is formulated as a Markov decision process (MDP). Three-dimensional features, encompassing dynamic orders, AM machines, and delays, are extracted using a ‘look around’ method to represent the production status at a rescheduling point. Additionally, five novel composite scheduling rules based on the out-of-order principle are introduced for selection when an AM machine completes processing or a new order arrives. Moreover, we design a reward function that is strongly correlated with the objective to evaluate the agent’s chosen action. Experimental results demonstrate the superiority of the O3-DDQN approach over single scheduling rules, randomly selected rules, and the classic DQN method. The average improvement rate of performance reaches 13.09% compared to composite scheduling rules and random rules. Additionally, the O3-DDQN outperforms the classic DQN agent with a 6.54% improvement rate. The O3-DDQN algorithm improves scheduling in dynamic AM environments, enhancing productivity and on-time delivery. This research contributes to advancing AM production and offers insights into efficient resource allocation.

Multimodal Deep Learning-based Radiomics Approach for Predicting Surgical Outcomes in Patients with Cervical Ossification of the Posterior Longitudinal Ligament.

A retrospective analysis. This research sought to develop a predictive model for surgical outcomes in patients with cervical ossification of the posterior longitudinal ligament (OPLL) using deep learning and machine learning (ML) techniques. Determining surgical outcomes assists surgeons in communicating prognosis to patients and setting their expectations. Deep learning and ML are computational models that identify patterns from large data sets and make predictions. Of the 482 patients, 288 patients were included in the analysis. A minimal clinically important difference (MCID) was defined as gain in Japanese Orthopaedic Association (JOA) score of 2.5 points or more. The predictive model for MCID achievement at 1 year postsurgery was constructed using patient background, clinical symptoms, and preoperative imaging features (x-ray, CT, MRI) analyzed through LightGBM and deep learning with RadImagenet. The median preoperative JOA score was 11.0 (IQR: 9.0-12.0), which significantly improved to 14.0 (IQR: 12.0-15.0) at 1 year after surgery ( P < 0.001, Wilcoxon signed-rank test). The average improvement rate of the JOA score was 44.7%, and 60.1% of patients achieved the MCID. Our model exhibited an area under the receiver operating characteristic curve of 0.81 and the accuracy of 71.9% in predicting MCID at 1 year. Preoperative JOA score and certain preoperative imaging features were identified as the most significant factors in the predictive models. A predictive ML and deep learning model for surgical outcomes in OPLL patients is feasible, suggesting promising applications in spinal surgery. 4.

Enhancing the Weld Quality of Polylactic Acid Biomedical Materials Using Rotary Friction Welding.

Polylactic acid (PLA) stands out as a biomaterial with immense potential, primarily owing to its innate biodegradability. Conventional methods for manufacturing PLA encompass injection molding or additive manufacturing (AM). Yet, the fabrication of sizable medical devices often necessitates fragmenting them into multiple components for printing, subsequently requiring reassembly to accommodate the constraints posed by the dimensions of the AM platform. Typically, laboratories resort to employing nuts and bolts for the assembly of printed components into expansive medical devices. Nonetheless, this conventional approach of jointing is susceptible to the inherent risk of bolts and nuts loosening or dislodging amid the reciprocating movements inherent to sizable medical apparatus. Hence, investigation into the joining techniques for integrating printed components into expansive medical devices has emerged as a critical focal point within the realm of research. The main objective is to enhance the joint strength of PLA polymer rods using rotary friction welding (RFW). The mean bending strength of welded components, fabricated under seven distinct rotational speeds, surpasses that of the underlying PLA substrate material. The average bending strength improvement rate of welding parts fabricated by RFW with three-stage transformation to 4000 rpm is about 41.94% compared with the average bending strength of PLA base material. The average surface hardness of the weld interface is about 1.25 to 3.80% higher than the average surface hardness of the PLA base material. The average surface hardness of the weld interface performed by RFW with variable rotational speed is higher than the average surface hardness of the weld interface performed at a fixed rotating friction speed. The temperature rise rate and maximum temperature recorded during RFW in the X-axis of the CNC turning machine at the outer edge of the welding part surpassed those observed in the internal temperature of the welding part. Remarkably, the proposed method in this study complies with the Sustainable Development Goals due to its high energy efficiency and low environmental pollution.

Emergency Fresh Whole Blood Transfusion Training for Ukrainian Health Professionals in Austere Environments.

Blood is a highly valuable medical resource that necessitates strict guidelines to ensure the safety and well-being of the recipient. Since the onset of the war in Ukraine there has been an increased demand for training in emergency fresh whole blood transfusion (EFWBT) to improve damage control resuscitation capabilities. To meet this demand, we developed, implemented, and evaluated a training program aimed at enhancing Ukrainian EFWBT proficiency. Eight Ukrainian healthcare professionals (UHPs), including six physicians and two medics, completed our training, derived from the Joint Trauma System Clinical Practice Guidelines, Tactical Combat Casualty Care (TCCC) Guidelines, 75th Ranger Regiment Ranger O-Low Titer (ROLO) program, and Marine Corps Valkyrie program. Participants were assessed on their confidence in the practical application and administrative oversight requirements of an EFWBT program. A cross-comparison was conducted between a larger data set of third-year medical students from the Uniformed Services University and the UHPs to determine the statistical significance of the program. The difference in mean scores of UHPs during preand post-training was statistically significant (p<0.001). Additionally, the average rate of improvement was greater for the UHPs compared with the third-year medical students (p=0.000065). Our study revealed that the application of an EFWBT training program for UHPs can significantly increase confidence in their ability to conduct EFWBTs on the battlefield. Further larger-scale research is needed to determine the impact of this training on performance outcomes.

Combination of Efficient Informationized Music Teaching and Traditional Music Culture in the Internet Era

Abstract Music teaching in education is undergoing a profound change under the development of information technology. Integrating information technology not only enhances teaching efficiency, but also expands the reach of teaching resources. The challenge for educators is to combine the use of modern information technology with the preservation and promotion of traditional music culture. This study discusses how to effectively combine efficient informatization teaching methods with China’s rich traditional music culture in the Internet era, intending to provide new perspectives and strategies for the innovative development of music education. By comparing and analyzing the learning effectiveness of the experimental group (using informatized teaching methods) and the control group (using traditional teaching methods), the study shows that the experimental group’s average improvement rates in music comprehension, skill mastery, and creativity reached 20%, 30%, and 40%, respectively, which were higher than those of the control group. The combination of informatization teaching tools and strategies in this study can significantly improve students’ interest and effectiveness in learning traditional music culture, injecting new vitality into conventional music education.

Enhancement of Students’ Cognitive Ability in Civics Informational Education in Colleges and Universities in the Era of Artificial Intelligence

Abstract In the context of the artificial intelligence era, the informationized education of Civics in colleges and universities is critical to enhance students’ cognitive ability. This study explores how to optimize the teaching of Civics and Politics and enhance students’ cognitive ability through ADDIE-F model. The purpose of the study is to optimize the teaching of Civics and Politics through the ADDIE-F teaching model, and then enhance students’ cognitive ability. Methodologically, this study adopts the design process of Civics teaching based on ADDIE-F model, and combines clustering and multiple regression models to predict and analyze students’ cognitive ability. The results showed that students in the experimental group performed significantly better than the control group in the three aspects of cognitive ability A, experiential ability B and control ability C, in which the average improvement rate of cognitive ability reached 20%. The conclusion shows that the Civics informatization education model based on the ADDIE-F model can effectively improve students’ cognitive ability, which helps to cultivate students’ comprehensive quality and ideological and moral level.

The Construction of Wisdom Teaching Mode of Physical Education and Training in Colleges and Universities in the Internet Era

Abstract The rise of the intelligent teaching model, relying on artificial intelligence and digital information technology, provides students with personalized and autonomous learning pathways. The model encourages students to learn independently and develop personally by integrating online and offline learning resources, enhancing their innovation and practical skills. Educational innovation has focused on exploring how to effectively incorporate competent teaching resources to improve teaching efficiency and students’ physical education skills. This study designed a new smart teaching mode for physical training science using blended learning theory and artificial intelligence technology. The differences in students’ physical education performance, participation, and satisfaction between the traditional and intelligent teaching modes were analyzed by comparison. The students who used innovative teaching methods in the study were better than those who used conventional teaching methods in 100-meter sprint and basketball shooting accuracy, with an average improvement rate of 15%. According to the study, the intelligent teaching mode can effectively enhance students’ physical education learning efficiency and mastery of movement skills, paving the way for a new development direction in college physical education.

Diagnosis of fetal arrhythmia in echocardiography imaging using deep learning with cyclic loss.

Fetal arrhythmias frequently co-occur with congenital heart disease in fetuses. The peaks observed in M-mode fetal echocardiograms serve as pivotal diagnostic markers for fetal arrhythmias. However, speckles, artifacts, and noise pose notable challenges for accurate image analysis. While current deep learning networks mainly overlook cardiac cyclic information, this study concentrated on the integration of such features, leveraging contextual constraints derived from cardiac cyclical features to improve diagnostic accuracy. This study proposed a novel deep learning architecture for diagnosing fetal arrhythmias. The architecture presented a loss function tailored to the cardiac cyclical information and formulated a diagnostic algorithm for classifying fetal arrhythmias. The training and validation processes utilized a dataset comprising 4440 patches gathered from 890 participants. Incorporating cyclic loss significantly enhanced the performance of deep learning networks in predicting peak points for diagnosing fetal arrhythmia, resulting in improvements ranging from 7.11% to 14.81% in F1-score across different network combinations. Particularly noteworthy was the 18.2% improvement in the F1-score for the low-quality group. Additionally, the precision of diagnosing fetal arrhythmia across four categories exhibited improvement, with an average improvement rate of 20.6%. This study introduced a cyclic loss mechanism based on the cardiac cycle information. Comparative evaluations were conducted using baseline methods and state-of-the-art deep learning architectures with the fetal echocardiogram dataset. These evaluations demonstrated the proposed framework's superior accuracy in diagnosing fetal arrhythmias. It is also crucial to note that further external testing is essential to assess the model's generalizability and clinical value.

Real-time retrieval of high-precision ZTD maps using GNSS observation

Zenith Tropospheric Delay (ZTD) is an important factor that restricts the high-precision positioning of global navigation satellite system (GNSS), and it is of great significance in establishing a real-time and high-precision ZTD model. However, existing ZTD models only consider the impact of linear terms on ZTD estimation, whereas the nonlinear factors have rarely been investigated before and thus become the focus of this study. A real-time and high-precision ZTD model for large height difference area is proposed by considering the linear and nonlinear characteristics of ZTD spatiotemporal variations and is called the real-time linear and nonlinearity ZTD (RLNZ) model. This model uses the ZTD estimated from the Global Pressure and Temperature 3 (GPT3) model as the initial value. The linear impacts of periodic term and height on the estimation of ZTD difference between GNSS and GPT3 model is first considered. In addition, nonlinear factors such as geographical location and time are further used to fit the remaining nonlinear ZTD residuals using the general regression neural network method. Finally, the RLNZ-derived ZTD is obtained at an arbitrary location. The western United States, with height difference ranging from −500 to 4000 m, is selected, and the hourly ZTD of 484 GNSS stations provided by the Nevada Geodetic Laboratory (NGL) and the data of 9 radiosonde (RS) stations in the year 2021 are used. Experiment results show that a better performance of ZTD estimation can be retrieved from the proposed RLNZ model when compared with the GPT3 model. Statistical results show the averaged root mean square (RMS), Bias, and mean absolute error (MAE) of ZTD from GPT3 and RLNZ models are 33.7/0.8/25.7 mm and 22.6/0.1/17.4 mm, respectively. The average improvement rate of the RLNZ model is 33 % when compared to the GPT3 model. Finally, the application of the proposed RLNZ model in simulated real-time Precise Point Positioning (PPP) indicates that the accuracy of PPP in N, E and U components is improved by 8 %, 2 %, and 6 % when compared with that from the GPT3-based PPP. Meanwhile, the convergence time in N and U components is improved by 23 % and 7 %, respectively. Such results verify the superiority of the proposed RLNZ model in retrieving real-time ZTD maps for GNSS positioning and navigation applications.

The consistent vehicle routing problem considering driver equity and flexible route consistency

In this study, we address a new consistent vehicle routing problem (ConVRP) by considering driver equity and flexible route consistency. It aims to optimize the departure time and routes for a set of vehicles over a defined planning period, aiming to minimize the total travel time while considering the discounts for the route consistent segments. Previous studies on ConVRP have primarily focused on ensuring customer satisfaction through time consistency and driver consistency, while overlooking driver equity. In our ConVRP, we introduce a flexible strategy to attain route consistency, i.e., drivers are encouraged to traverse familiar routes as many as possible during the planning period by offering time discounts for routes crossed more than twice. Driver equity is addressed through the optimal allocation of delivery capacity. For this problem, we formulate it into a mixed-integer linear programming model. Given its strong NP-hardness, a tailored adaptive large neighborhood search algorithm (ALNS) is developed to solve practical-sized problems. Destroy and repair operators are adaptively applied to remove customers from the routes and reinsert them in better positions. A new repair operator that identifies suitable customer locations by considering vehicle load and an exchange operator that reverses part of the specified routes are proposed to obtain better solutions and increase search efficiency, respectively. Moreover, we enhance arrival time consistency by adjusting departure time. Extensive numerical experiments for instances of varying scales are conducted to evaluate the proposed algorithm. Results demonstrate that i) the proposed algorithm can obtain high-quality solutions (the average relative difference compared to the optimal solution is only 1.68%); ii) Our approach can also find better solutions (with an average improvement rate of 3.53% and 33.70%, respectively) in a short computation time, when compared to the basic ALNS without a new operator and the widely used variable neighborhood descent algorithm; and iii) setting a small discount allows decision-makers to significantly enhance consistent distance for drivers.

Novel wind-speed prediction system based on dimensionality reduction and nonlinear weighting strategy for point-interval prediction

In the context of today’s energy shortage, wind energy plays a crucial role as one of the most widely used renewable energy sources. However, in order to fully utilize the potential of wind energy, it is necessary to build a precise and reliable wind-speed prediction system. Conventional wind-speed prediction models frequently rely on a solitary model for forecasting, and sometimes these models cannot accurately fit the nonlinear characteristics of the data, resulting in poor prediction performance. Therefore, to address this deficiency, a new wind-speed point-interval prediction system is proposed in this study. The fuzzy information granulation technology is adopted in this system to reduce the dimension of data and solve the problem of redundancy in wind-speed data. In addition, this paper uses the multi-objective dragonfly algorithm and combines sub-models using the multi-nonlinear weight strategy to address the issue of inadequate precision exhibited by an individual prediction model. In order to verify the effectiveness of this wind-speed prediction system, the Penglai wind farm in Shandong Province is used as the dataset to construct the model, and several reference models are selected to conduct point prediction and interval prediction comparison experiments respectively. The experimental results show that the combined prediction system has the best prediction performance, with MAPE values of 14.16%, 15.02% and 15.74%, respectively. Compared with other benchmark models, the average improvement rates for the multi-step prediction were 14.97%, 16.48% and 19.11%, respectively.