Release Schedule Research Articles

Mitigating risk of credit reversal in nature-based climate solutions by optimally anticipating carbon release

Nature-based climate solutions supply carbon credits generated from net carbon drawdown in exchange for project funding, but their credibility is challenged by the inherent variability and impermanence of drawdown. By evaluating drawdown benefits from a social cost of carbon perspective, project developers can enhance credibility and estimate impermanence by conservatively anticipating drawdowns to be eventually released following a release schedule, issuing additional credits when actual release is less severe than anticipated. We demonstrate how we can use ex post observations of drawdowns to construct optimal release schedules that limit the risk of credit reversals (when net drawdown is negative). We simulate both theoretical and real-life projects to examine how this approach balances the trade-off between generating credits evaluated as more permanent and limiting reversal risk. We discuss how this approach incentivizes project performance and provides a pragmatic solution to challenges facing larger-scale implementation of nature-based climate solutions.

Reservoir Operation based Machine Learning Models: Comprehensive Review for Limitations, Research Gap, and Possible Future Research Direction

The operation of dams and reservoirs is critical for water resource management, including flood control, irrigation, hydropower generation, and environmental conservation. Traditional optimization techniques like Dynamic Programming (DP), Linear Programming (LP), and Nonlinear Programming (NLP) have been foundational in managing these operations. However, they often fall short in addressing the complexities of modern water management challenges posed by climate variability and increasing water demands. Machine learning (ML) techniques have emerged as powerful tools to enhance the efficiency and accuracy of dam and reservoir operations. This paper provides a comprehensive review of various ML models, including Neural Networks, Genetic Algorithms, Decision Trees, and Ensemble Methods, highlighting their applications in predicting reservoir inflows, optimizing water release schedules, and improving flood risk management. Notably, ML models like Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNNs) have shown significant improvements in forecasting accuracy and operational decision-making. Despite these advancements, several limitations and research gaps persist, including the need for real-time data integration, adaptive learning mechanisms, and models that consider socio-economic and climatic factors. This review underscores the importance of addressing these gaps to develop more robust and generalizable ML models. Future research directions are suggested to focus on hybrid models combining ML with traditional optimization techniques, comprehensive validation across diverse conditions, and the integration of ecological and economic considerations. By systematically identifying and addressing these limitations, this research aims to pave the way for more effective and sustainable dam and reservoir management practices. Leading towards suggesting that enhancing real-time data integration and developing adaptive learning mechanisms are in order to improve model responsiveness.

Economic optimization of Wolbachia-infected Aedes aegypti release to prevent dengue.

Dengue virus, primarily transmitted by the Aedes aegypti mosquito, is a major public health concern affecting ≈3.83 billion people worldwide. Recent releases of Wolbachia-transinfected Ae. aegypti in several cities worldwide have shown that it can reduce dengue transmission. However, these releases are costly, and, to date, no framework has been proposed for determining economically optimal release strategies that account for both costs associated with disease risk and releases. We present a flexible stochastic dynamic programming framework for determining optimal release schedules for Wolbachia-transinfected mosquitoes that balances the cost of dengue infection with the costs of rearing and releasing transinfected mosquitoes. Using an ordinary differential equation model of Wolbachia and dengue in a hypothetical city loosely describing areas at risk of new dengue epidemics, we determined that an all-or-nothing release strategy that quickly brings Wolbachia to fixation is often the optimal solution. Based on this, we examined the optimal facility size, finding that it was inelastic with respect to the mosquito population size, with a 100% increase in population size resulting in a 50-67% increase in optimal facility size. Furthermore, we found that these results are robust to mosquito life-history parameters and are mostly determined by the mosquito population size and the fitness costs associated with Wolbachia. These results reinforce that Wolbachia-transinfected mosquitoes can reduce the cost of dengue epidemics. Furthermore, they emphasize the importance of determining the size of the target population and fitness costs associated with Wolbachia before releases occur. © 2024 The Authors. Pest Management Science published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Positive Shift of the Image of China in Recent Hollywood Blockbusters

Hollywood will encounter some cultural policies when its films are imported to the Chinese film market on a revenue-sharing basis. These include a quota system, a censorship system and an uncertain release schedule. However, China has been the fastest growing film market since 2008 and the second largest film market in the world since 2012 (yet the current film industries worldwide are recovering from the impacts from the COVID-19 pandemic). Despite the restrictive cultural policies, Hollywood, attracted by the promising profitability, have incorporated more Chinese roles and more plots about China to please the Chinese film regulators and audiences in order to gain access to the lucrative Chinese film market. Furthermore, the depiction of China has become more positive and diverse in recent Hollywood blockbusters compared with the Orientalist stereotypical images in the past. The author intends to examine the reasons behind the phenomenon through analysing the positively changing images of China from early Hollywood films to the recent Hollywood blockbusters. In fact, the positively changing depiction of China illustrates China and the US negotiating the dynamic process of cross-cultural exchange in economic and political terms through compromise, competition and collaboration.

Netflix Movies and Tv Shows Data Analysis

Abstract: Netflix stands as the leading on-demand streaming platform in current times, offering its services across a staggering 190 countries and featuring an extensive library of both movies and TV shows. In our research, we carried out an initial exploratory analysis utilizing data sourced from Flexible, a search engine dedicated to cataloging the content accessible on the Netflix platform. When Netflix made its debut in April, online video streaming was still in its early stages. Fast forward eighteen years, and Netflix has evolved into the world's foremost global Internet television platform. we are diving into Netflix datasets obtained from Kaggle to gain a deeper understanding of the release schedules for movies and TV shows on the platform. Our goals encompass determining the time it takes for content to become accessible, scrutinizing the frequency of releases in specific time intervals, examining releases over the last decade, and identifying the top 10 genres that resonate most with Netflix viewers..The preliminary analysis has revealed fascinating observations regarding the current content trends on Netflix. While the current state of the recommendation system has its limitations, there is potential for improvement when incorporating additional features and variables.

Co-encapsulation of hydrophilic and hydrophobic drugs into niosomal nanocarrier for enhanced breast cancer therapy: In silico and in vitro studies

Combination therapy has been considered one of the most promising approaches for improving the therapeutic effects of anticancer drugs. This is the first study that uses two different antioxidants in full-characterized niosomal formulation and thoroughly evaluates their synergistic effects on breast cancer cells. In this study, in-silico studies of hydrophilic and hydrophobic drugs (ascorbic acid: Asc and curcumin: Cur) interactions and release were investigated and validated by a set of in vitro experiments to reveal the significant improvement in breast cancer therapy using a co-delivery approach by niosomal nanocarrier. The niosomal nanoparticles containing surfactants (Span 60 and Tween 60) and cholesterol at 2:1 M ratio were prepared through the film hydration method. A systematic evaluation of nanoniosomes was carried out. The release profile demonstrated two phases (initial burst followed by sustained release) and a pH-dependent release schedule over 72 h. The optimized niosomal preparation displayed superior storage stability for up to 2 months at 4 °C, exhibiting extremely minor changes in pharmaceutical encapsulation efficiency and size. Free dual drugs (Asc + Cur) and dual-drug loaded niosomes (Niosomal (Asc + Cur)) enhanced the apoptotic activity and cytotoxicity and inhibited cell migration which confirmed the synergistic effect of co-encapsulated drugs. Also, significant up-regulation of p53 and Bax genes was observed in cells treated with Asc + Cur and Niosomal (Asc + Cur), while the anti-apoptotic Bcl-2 gene was down-regulated. These results were in correlation with the increase in the enzyme activity of SOD, CAT, and caspase, and the levels of malondialdehyde (MDA) and reactive oxygen species (ROS) upon treatment with the mentioned drugs. Furthermore, these anti-cancer effects were higher when using Niosomal (Asc + Cur) than Asc + Cur. Histopathological examination also revealed that Niosomal (Asc + Cur) had a lower mitosis index, invasion, and pleomorphism than Asc + Cur. These findings indicated that niosomal formulation for co-delivery of Asc and Cur would offer a promising delivery system for an effective breast cancer treatment.

Analysis of the Factors Influencing the Box Office of Domestic Animated Films

This paper mainly discusses the influencing factors of domestic animation film box office. In the early days, the domestic animation market was mainly occupied by American animated films. Although development was difficult, domestic animation films have undergone many changes in the 21st century. To help people better understand the development status and market situation of domestic animated films, this experiment aims to study the influencing factors of box office. This experiment takes 5 influencing factors that are easy to quantify as research objects: genre, production method, duration, release schedule and rating. Data on these factors can be found online and processed. Preliminary processed data is then drawn into charts. To be rigorous, this experiment also makes linear regression analysis on some influencing factors to see the relationship between box office and factors. The study finds a moderate correlation between box office and duration, and a weak correlation between rating. 3D animated films generally outperform 2D films at the box office. Animated films that focus on "family" have lower box office receipts than films in other genres. Movies released during the summer and Spring Festival outperform those released during other seasons.

Toroidal-spiral particles as a CAR-T cell delivery device for solid tumor immunotherapy

Chimeric antigen receptor (CAR) T cell therapy has resulted in positive effects on patients with hematologic malignancy but shows limited efficacy in solid tumor treatments due to insufficient trafficking and tumor infiltration, intensive CAR-T-related toxicities, and antigen escape. In this work, we developed and investigated a biodegradable and biocompatible polymeric toroidal-spiral particle (TSP) as a in vivo cell incubator and delivery device that can be implanted near tumor through a minimally invasive procedure or injected near or into solid tumors by using a biopsy needle. The main matrix structure of the millimeter-sized TSP is made from crosslinking of gelatin methacrylamine (GelMA) and poly (ethylene glycol) diacrylate (PEGDA) with a tunable degradation rate from a few days to months, providing appropriate mechanical properties and sustained release of co-encapsulated drugs and/or stimulation compounds. The toroidal-spiral layer of the particles, presenting an internal void volume for high-capacity cell loading and flexibility of co-encapsulating small and large molecular compounds with individually manipulated release schedules, is filled with collagen and suspended T cells. The TSPs promote cell proliferation, activation, and migration in the tumor micro-environment in a prolonged and sustained manner. In this study, the efficacy of mesothelin (MSLN) CAR-T cells released from the TSPs was tested in preclinical mouse tumor models. Compared to systemic and intratumoral injection, peritumoral delivery of MSLN CAR-T cells using the TSPs resulted in a superior antitumor effect. The TSPs made of FDA approved materials as an in vivo reactor may provide an option for efficiently local delivery of CAR-T cells to solid tumors for higher efficacy and lower toxicity, with a minimally invasive administration procedure.

A functional Hidden Markov Model to incorporate dynamics into Bayesian optimal stopping problems: Helping physicians manage traumatic brain injuries

This paper describes a decision support system for neurosurgeons to determine the release schedule for polytrauma patients with concurrent traumatic brain injuries (TBIs). We present a novel functional Hidden Markov Model (fHMM) designed to mitigate the computational burden caused by ever-growing historical data. Our fHMM is nested into a Bayesian optimal stopping problem, effectively representing emergency physicians' crucial decisions during the discharge process. Our model is unique in its ability to adapt to different physician decision-making styles while continuously monitoring patient progress. We validate our approach using simulated and real data from a major hospital in Tampa Bay. The analysis reveals that dynamic prognostic measures can help balance the competing needs of rapid patient release and neurologic stability. Additionally, our results show variability in physicians' expectations regarding neurological recovery. Counterfactual analyses suggest that implementing this decision model could potentially save up to $27,500 per TBI patient under certain conditions.

Research on Visualization Technology of Production Process for Mechanical Manufacturing Workshop

The visualization of workshop information can affect production management and efficiency. Information can be presented both graphically and non-graphically (for example, in the form of data lists or tables). Graphical representations are intuitive and clear, but currently, most of them are based on statistical data, which makes it difficult to convey logical linkages between information and cannot help managers make decisions effectively. With the aim of designing the workshop production system with visual processes in small-sized enterprises, the key visualization technologies of the process flow chart, including the visual design of process flow chart, process card management, process flow chart release, process control, and production schedule monitoring, were all addressed in detail. On this basis, the mechanical manufacturing workshop production management system was created using C#.NET as the programming language. The main contribution of the research is that the system designed used the process flow chart as the main line through all functional modules and integrated all process data on the process nodes of the process flow chart to realize the graphical monitoring of workshop production schedule. The visualization technology of the process flow chart makes the system simple to use and easy to understand, which significantly improves information management and work efficiency in the workshop. Additionally, it provides the technical foundation for flow-driven production information transfer in the workshop and can serve as a universal standard for the process module in workshop production management systems.

Software for "A Study on Optimal Release Schedule for Multiversion Software"

Research on software reliability growth models (SRGMs) has been extensively conducted for decades, and the models were often developed based on two assumptions: (1) once the errors are detected, they can be completely removed instantly, and (2) errors can be removed eternally, and the debugging tasks will not produce any new errors. How-ever, both assumptions are unrealistic. This study proposes an SRGM that ignores these restricted assumptions by introducing a detection process that may remove an error after a period of time once it has been detected and by considering imperfect debugging, which indicates that new errors may emerge through corresponding debugging tasks. In addi-tion, because software can be upgraded to respond on a timely basis to constantly changing consumer expectations and thus extend product life in the market, the proposed SRGM also considers software upgrades for the multiversion software, and a dynamic program-ming approach is used to effectively obtain the optimal release schedule with consideration of the constraint of budget. Real data sets are used to examine the effectiveness of the pro-posed model, and the fitting results show that the proposed model outperforms other existing models. The results of numerical validation indicate that the proposed dynamic programming method with information updating outperforms the sequential solution method in determining the optimal release time for each version. Moreover, decision makers should carefully evaluate the parameters because overestimating the parameters of the mean value functions will cause serious software risk due to excessively shortening the testing time.

A Study on Optimal Release Schedule for Multiversion Software

Research on software reliability growth models (SRGMs) has been extensively conducted for decades, and the models were often developed based on two assumptions: (1) once the errors are detected, they can be completely removed instantly, and (2) errors can be removed eternally, and the debugging tasks will not produce any new errors. However, both assumptions are unrealistic. This study proposes an SRGM that ignores these restricted assumptions by introducing a detection process that may remove an error after a period of time once it has been detected and by considering imperfect debugging, which indicates that new errors may emerge through corresponding debugging tasks. In addition, because software can be upgraded to respond on a timely basis to constantly changing consumer expectations and thus extend product life in the market, the proposed SRGM also considers software upgrades for the multiversion software, and a dynamic programming approach is used to effectively obtain the optimal release schedule with consideration of the constraint of budget. Real data sets are used to examine the effectiveness of the proposed model, and the fitting results show that the proposed model outperforms other existing models. The results of numerical validation indicate that the proposed dynamic programming method with information updating outperforms the sequential solution method in determining the optimal release time for each version. Moreover, decision makers should carefully evaluate the parameters because overestimating the parameters of the mean value functions will cause serious software risk due to excessively shortening the testing time. History: Accepted by Pascal Van Hentenryck, Area Editor for Computational Modeling: Methods & Analysis. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2021.0141 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2021.0141 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .

Fast response flight multi-service nodes prediction based on one hidden layer neural network

Airport scene multi-service process(ASMP) state prediction is one of the important links to optimize airport ground resource allocation, improve collaborative release scheduling, and improve airport operation efficiency. In order to solve the problem of the slow response of existing prediction models, a Gaussian kernel probability density model of multi-service nodes in airport scenes is established. Then the one hidden layer neural network(OHLNN) is used to predict the nodes of ASMP. A study on the data of more than 20,000 flights at a large airport in China shows that: The mean absolute error (MAE) of the mixed flight prediction result is only 2.62911min, the mean root mean square error (RMSE) is only 3.24564min, and the response speed of the prediction model in the verification set is about 0.48s. When the results of MAE and RMSE are good, the response speed of the prediction model is greatly improved.

Order release optimisation for time-dependent and stochastic manufacturing systems

Order release optimisation is essential in production planning, especially in discrete manufacturing. Order release planning models with load-dependent lead times must anticipate the time-dependent work-in-process and output for any given release schedule and thus require an anticipation model that approximates the time-dependent behaviour of queueing systems. We present a generic optimisation model for order release planning in stochastic, non-stationary manufacturing systems that includes a well-defined interface for the anticipation model. We develop two stationary backlog carryover (SBC) approaches to approximate time-dependent queueing behaviour and prove their consistency with the order release model. The resulting nonlinear programming model is shown to be a special case of the well-known clearing function models. A numerical study demonstrates that the optimised order releases for different demand patterns are close to the optimum that results from simulation-based optimisation even for extreme demand and release patterns. The resulting output closely matches the simulated output with some deviations.

Methylphenidate Superior Efficacy Dosing Schedule: Three Hour Schedule for Immediate Release Tablets and Six Hour Schedule for Extended-Release Capsules

Background: Methylphenidate Hydrochloride is used mostly for treating Attention Deficit and Hyperactivity Disorder and Narcolepsy. It is available in Immediate Release tablets, liquids, extended-release doses, and transdermal patches. Clinicians instruct patients to take Immediate Release tablets four hours apart or eight to nine hours after an extended-release dose. Four-hour dosing has been used for decades while many patients complain of a “roller coaster” of symptoms stopping and returning several times each day. Four-hour dosing is inaccurate because Immediate Release tablets are effective for two to three hours. Methods: The “roller coaster” was addressed with information from a 2014 to 2022 research program and from analyzing over 400 Dopamine deficiency articles. Results: The four-hour Immediate Release schedule and the eight-to-nine-hour extended-release schedule are inaccurate for research and treatment. Four-hour dosing causes two hours of non-efficacy during transitions between doses. The eight-to-nine-hour schedule causes three to four hours of non-efficacy during transitions. Three-hour and six-hour schedules sustain efficacy across and between sequential doses. Conclusion: Under four-hour dosing, soon after hour-three a patient’s plasma concentration drops below and stays below the efficacy threshold for an hour and forty-five minutes. The loss of efficacy occurs during every transition from one dose to the next. Under four-hour dosing, patients who take four sequential doses experience 205 minutes of loss of efficacy every two hours three times every day, totaling 615 minutes per day. To the best knowledge of this author, he is the first person to find three-hour dosing stops the roller coaster. Efficacy occurs during transitions because dose-onset adds plasma concentration at the same rate that termination loses plasma concentration. Sequential doses taken at hour-3 combine into a level that stays above the efficacy threshold. When sequential doses are taken sometime after hour-3, the termination-dose drops below the efficacy-threshold and the sequential onset-dose does not create enough plasma concentration to bring a terminating plasma concentration to a higher level. Proper timing is critical for patients to receive high quality benefits of Methylphenidate. Three-hour dosing matches the biochemistry of Methylphenidate and enables high quality benefits.

Technical debt in the engineering of complex systems

AbstractThe metaphor of technical debt (TD) is widely adopted in the software engineering field, referring to short‐term compromises in software artifacts in exchange for speed or to meet release schedules or other constraints. The implication is that TDs accumulate over time, and may eventually make rework or maintenance very expensive or even impossible. The analogy is generally applicable in the systems engineering field, particularly concerning numerous program cancellation and obsolescence challenges due to premature decisions made in early acquisition phases. This paper adapts this metaphor of TD to the systems engineering field, and proposes a TD taxonomy to support the early identification and assessment of TD items in engineering complex systems, especially in the early life cycle phases of engineering complex, distributed systems. The taxonomy identifies seven TD types: functionality, performance, interoperability, version conflicts, documentation and support, system evolution, and organic, based on systematic indicators and signs discoverable during early acquisition activities. We expect that the notion and the taxonomy of TD will offer an additional perspective for design decisions that will help mitigate challenging integration and obsolescence issues in the engineering of complex systems.

Sex-structured model of Wolbachia invasion and design of sex-biased release strategies in Aedes spp mosquitoes populations

Laboratory experiments as well as some field essays have revealed that the intracellular bacterium Wolbachia, deliberately introduced in Aedes spp female mosquitoes, drastically reduces their vector competence for dengue virus and, also, other mosquito-borne viral diseases. However, female mosquitoes infected with Wolbachia still need to ingest human blood while male mosquitoes, either wild or Wolbachia-carrying, do not bite people. As such, Wolbachia-carrying females may transmit the virus to people during blood-feeding, even though with far less probability than the wild ones. Therefore, massive releases of Wolbachia-carrying females may increase both the nuisance and the epidemiological risk among human residents. With the goal of exploring in depth the practical aspects of sex-biased releases, we introduce in this paper a simple sex-structured model of Wolbachia invasion that brings forward the possibility of developing male-biased release strategies of Wolbachia-carriers leading to Wolbachia invasion. Thanks to this model, we study at length the minimal amount of mosquitoes necessary to complete this task, according to the relative sex-ratio of the released mosquitoes and the release schedule. We also pay attention to the estimate of the time needed to achieve the ultimate population replacement.

Automated data validation: An industrial experience report

There has been a massive explosion of data generated by customers and retained by companies in the last decade. However, there is a significant mismatch between the increasing volume of data and the lack of automation methods and tools. The lack of best practices in data science programming may lead to software quality degradation, release schedule slippage, and budget overruns. To mitigate these concerns, we would like to bring software engineering best practices into data science. Specifically, we focus on automated data validation in the data preparation phase of the software development life cycle.This paper studies a real-world industrial case and applies software engineering best practices to develop an automated test harness called RESTORE. We release RESTORE as an open-source R package. Our experience report, done on the geodemographic data, shows that RESTORE enables efficient and effective detection of errors injected during the data preparation phase. RESTORE also significantly reduced the cost of testing. We hope that the community benefits from the open-source project and the practical advice based on our experience.

Reducing Wait Times for Radiology Exams Around Holiday Periods: A Monte Carlo Simulation.

Reducing patient wait times is a key operational goal and impacts patient outcomes. The purpose of this study is to explore the effects of different radiology scheduling strategies on exam wait times before and after holiday periods at an outpatient imaging facility using computer simulation.An idealized Monte Carlo simulation of exam scheduling at an outpatient imaging facility was developed based on the actual distribution of scheduled exams at outpatient radiology sites at a tertiary care medical center. Using this simulation, we examined three scheduling strategies: (1) no scheduling modifications, (2) increase imaging capacity before or after the holiday (i.e. increase facility hours), and (3) use a novel rolling release scheduling paradigm. In the third scenario, a fraction of exam slots are blocked to long-term follow-up exams and made available only closer to the exam date, thereby preventing long-term follow-up exams from filling the schedule and ensuring slots are available for non-follow-up exams. We examined the effect of these three scenarios on utilization and wait times, which we defined as the time from order placement to exam completion, during and after the holiday period.The baseline mean wait time for non-follow-up exams was 5.4days in our simulation. When no scheduling modifications were made, there was a significant increase in wait times in the week preceding the holiday when compared to baseline (10.0days vs 5.4days, p < 0.01). Wait times remained elevated for 4weeks following the holiday. Increasing imaging capacity during the holiday and post-holiday period by 20% reduced wait times by only 6.2% (9.38days vs 10.0days, p < 0.01). Increasing capacity by 50% resulted in a 7.1% reduction in wait times (9.28days, p < 0.01), and increasing capacity by 100% resulted in a 13% reduction in wait times (8.75days, p < 0.01). In comparison, using a rolling release model produced a reduction in peak wait times equivalent to doubling capacity (8.76days, p < 0.01) when 45% of slots were reserved. Improvements in wait times persisted even when rolling release was limited to the 3weeks preceding or 1week following the holiday period. Releasing slots on a rolling basis did not significantly decrease utilization or increase wait times for long-term follow-up exams except in extreme scenarios where 80% or more of slots were reserved for non-follow-up exams.A rolling release scheduling paradigm can significantly reduce wait time fluctuations around holiday periods without requiring additional capacity or impacting utilization.

Dynamic scheduling for semiconductor manufacturing systems with uncertainties using convolutional neural networks and reinforcement learning

The dynamic scheduling problem of semiconductor manufacturing systems (SMSs) is becoming more complicated and challenging due to internal uncertainties and external demand changes. To this end, this paper addresses integrated release control and production scheduling problems with uncertain processing times and urgent orders and proposes a convolutional neural network and asynchronous advanced actor critic-based method (CNN-A3C) that involves a training phase and a deployment phase. In the training phase, actor–critic networks are trained to predict the evaluation of scheduling decisions and to output the optimal scheduling decision. In the deployment phase, the most appropriate release control and scheduling decisions are periodically generated according to the current production status based on the networks. Furthermore, we improve the four key points in the deep reinforcement learning (DRL) algorithm, state space, action space, reward function, and network structure and design four mechanisms: a slide-window-based two-dimensional state perception mechanism, an adaptive reward function that considers multiple objectives and automatically adjusts to dynamic events, a continuous action space based on composite dispatching rules (CDR) and release strategies, and actor–critic networks based on convolutional neural networks (CNNs). To verify the feasibility and effectiveness of the proposed dynamic scheduling method, it is implemented on a simplified SMS. The simulation experimental results show that the proposed method outperforms the unimproved A3C-based method and the common dispatching rules under the new uncertain scenarios.