Online Solution Research Articles

ε-Nash Equilibrium of Pursuer–Evader–Defender Missile Navigation Dynamic Games

This research is dedicated to developing a min–max robust control strategy for a dynamic game involving pursuers, evaders, and defenders in a multiple-missile scenario. The approach employs neural dynamic programming, utilizing multiple continuous differential neural networks (DNNs). The competitive controller devised addresses the robust optimization of a joint cost function that relies on the trajectories of the pursuer–evader–defender system, accommodating an uncertain mathematical model while adhering to control restrictions. The dynamic programming min–max formulation facilitates robust control by accounting for bounded modeling uncertainties and external disturbances for each game component. The value function of the Hamilton–Jacobi–Bellman (HJB) equation is approximated by a DNN, enabling the estimation of the closed-loop formulation for the joint dynamic game with state restrictions. The controller’s design is grounded in estimating the state trajectory under the worst possible uncertainties and perturbations, providing a robustness factor through the robust neural controller. The learning law class for the time-varying weights in the DNN is generated by studying the HJB partial differential equation for the missile motion for each player in the dynamic game. The controller incorporates the solution of the obtained learning laws and a time-varying Riccati equation, offering an online solution to the control implementation. A recurrent algorithm, based on the Kiefer–Wolfowitz method, adjusts the initial conditions for the weights to satisfy the final condition of the given cost function for the dynamic game. A numerical example is presented to validate the proposed robust control methodology, confirming the optimization solution based on the DNN approximation for Bellman’s value function.

A Reliable and Efficient Online Solution for Adaptive Voltage and Frequency Scaling on FPGAs

A Reliable and Efficient Online Solution for Adaptive Voltage and Frequency Scaling on FPGAs

Research on Algorithm Driven Intelligent Management and Control Technology for Future Power Grid

An ever-more crucial architecture for both present and future electrical systems is a Power Grid (PG) that spans multiple areas comprising interlinked transmission lines, which may effectively reallocate energy resources on an extensive level. Preserving system equilibrium and increasing operating earnings are largely dependent on how the PG dispatches power using a variety of resources. The optimization techniques used to solve this dispatch issue today are not capable of making decisions or optimizing online; instead, they require doing the entire optimization computation at every dispatch instant. Herein, a novel Mutable Galaxy-based Search-tuned Flexible Deep Convolutional Neural Network (MGS-FDCNN) is presented as an online solution to targeted coordinated dispatch challenges in future PG. System optimization can be achieved using this strategy using only past operational data. First, a numerical model of the targeted coordination dispatch issue is created. Next, to solve the optimization challenges, we construct the MGS optimization approach. The effectiveness and accessibility of the suggested MGS-FDCNN approach are validated by the presentation of experimental data relying on the IEEE test bus network.

A novel adjusted real-time decision-making for dynamic distribution in the grocery supply chain

PurposeThe current research has developed a novel method to update the decisions regarding real-time data, named the dynamic adjusted real-time decision-making (DARDEM), for updating the decisions of a grocery supply chain that avoids both frequent modifications of decisions and apathy. The DARDEM method is an integration of unsupervised machine learning and mathematical modeling. This study aims to propose a dynamic proposed a dynamic distribution structure and developed a bi-objective mixed-integer linear program to make distribution decisions along with supplier selection in the supply chain.Design/methodology/approachThe constantly changing environment of the grocery supply chains shows the necessity for dynamic distribution systems. In addition, new disruptive technologies of Industry 4.0, such as the Internet of Things, provide real-time data availability. Under such conditions, updating decisions has a crucial impact on the continued success of the supply chains. Optimization models have traditionally relied on estimated average input parameters, making it challenging to incorporate real-time data into their framework.FindingsThe proposed dynamic distribution and DARDEM method are studied in an e-grocery supply chain to minimize the total cost and complexity of the supply chain simultaneously. The proposed dynamic structure outperforms traditional distribution structures in a grocery supply chain, particularly when there is higher demand dispersion. The study showed that the DARDEM solution, the online solution, achieved an average difference of 1.54% compared to the offline solution, the optimal solution obtained in the presence of complete information. Moreover, the proposed method reduced the number of changes in downstream and upstream decisions by 30.32% and 40%, respectively, compared to the shortsighted approach.Originality/valueIntroducing a dynamic distribution structure in the supply chain that can effectively manage the challenges posed by real-time demand data, providing a balance between distribution stability and flexibility. The research develops a bi-objective mixed-integer linear program to make distribution decisions and supplier selections in the supply chain simultaneously. This model helps minimize the total cost and complexity of the e-grocery supply chain, providing valuable insights into decision-making processes. Developing a novel method to determine the status of the supply chain and online decision-making in the supply chain based on real-time data, enhancing the adaptability of the system to changing conditions. Implementing and analyzing the proposed MILP model and the developed real-time decision-making method in a case study in a grocery supply chain.

Coordinated management of oxygen excess ratio and cathode pressure for PEMFC based on synthesis variable-gain robust predictive control

In this research endeavor, a novel synthesis variable-gain robust model predictive control (SVGRPC) method using the min-max technique with parameter dependent Lyapunov functions is introduced to achieve the desired trajectory tracking of oxygen excess ratio (OER) and cathode pressure in the polymer electrolyte membrane fuel cells (PEMFCs) system. Initially, a simplified control-oriented model of the air supply system is developed and then transformed into a polytopic form to accommodate the inherent uncertainties in the PEMFC. Subsequently, the polytopic model is integrated with the reference trajectory to construct an augmented state-space model for deriving an error state representation. In the framework of robust model predictive control (RPC) utilizing a parameter-dependent Lyapunov function, a series of variable feedback gains are employed to mitigate conservatism. Additionally, the online solution process imposes a significant computational burden, presenting challenges for the real-time implementation of RPC-based control strategy. Therefore, the offline computing is introduced to significantly reduce the computational burden, resulting in the development of the SVGRPC strategy proposed in this paper. Subsequently, the SVGRPC strategy computes explicit linear state-feedback control laws by solving linear matrix inequalities (LMIs) using an offline control algorithm. The effectiveness of the proposed controller is then validated through assessments conducted under three distinct operating conditions of the PEMFC system. The outcomes of this study affirm that the proposed controller improves the requirements of control performance when compared to the online RPC with a quadratic Lyapunov function while significantly alleviating the computational workload.

An auction approach to aircraft bandwidth scheduling in non-terrestrial networks

Internet Service has witnessed only limited deployment on commercial flights, where network infrastructure is lacking and subscription fees are high. It is natural to design an efficient scheduling strategy for Internet service access on flights, while maximizing social welfare. There are challenges to use either antennas on the ground or geostationary (GEO) satellites in space as Internet Service Provider (ISP) equipment. First, preemptive-purchase and resource-allocation in post-paid plans may not satisfy the dynamic demand for large amounts of flight-ISP machine links. Second, finding an optimal, dynamic, online solution based on flight demands is NP-hard. Third, existing solutions often fail to maximize either seller profit or social welfare. To address the aforementioned challenges, we formulate an online bandwidth scheduling integer linear program (ILP) among flights, antennas, and GEO satellites in a Non-Terrestrial Network (NTN). We transform the ILP into an exponential optimization problem, which is then relaxed, with its dual formulated. We iteratively solve a series of dual subproblems in polynomial time, towards social welfare maximization with a good competitive ratio in typical network settings. In empirical studies, our algorithm achieved a much better competitive ratio than the theoretical worst-case guarantee, and clearly outperforms alternative algorithms.

Power-Efficient Dispatching of Time-Sensitive Requests in the Fog-Enabled Industrial Internet of Things

Recent advancements in service offerings and the emergence of new application areas have reveal the limitations of cloud computing as a solely solution. One of these new areas is the industrial internet of things, where industrial processes are controlled in a network-based and automated way which brings many new challenges. To solve the challenges, fog computing has been introduced as a complementary paradigm to the cloud. Resource management is one of those challenges need further investigation. The industrial internet of things by its own characteristics has led traditional methods to be inefficient within this evolving ecosystem. Therefore, fully utilizing potential of the new system necessitates effective resource management. This manuscript aims to investigate the problem of resource management in the emerging cloud-fog ecosystem of the industrial internet of things. Considering the dynamic nature of users, this study proposes the algorithms for dynamic resource allocation and provisioning based on deadlines. We formulate the problem as a multiple criteria stochastic problem and introduced an online solution. Our proposed solution takes into account the unique characteristics of Fog computing and the dynamic behavior of users. To effectively handle the scheduling of requests, the research suggests utilizing the Lyapunov optimization method and Lyapunov drift theory. The Lyapunov method helps to merge and measure all the related objectives in terms drift. The objective function is optimized, in each time slot, using a drift-plus-penalty weight parameter. By adopting this approach, the system can operate efficiently while meeting the constraints and performance requirements of IoT applications.

Computationally efficient solution of mixed integer model predictive control problems via machine learning aided Benders Decomposition

Mixed integer Model Predictive Control (MPC) problems arise in the operation of systems where discrete and continuous decisions must be taken simultaneously to compensate for disturbances. The efficient solution of mixed integer MPC problems requires the computationally efficient online solution of mixed integer optimization problems, which are generally difficult to solve. In this paper, we propose a machine learning-based branch and check Generalized Benders Decomposition algorithm for the efficient solution of such problems. We use machine learning to approximate the effect of the complicating variables on the subproblem by approximating the Benders cuts without solving the subproblem, therefore, alleviating the need to solve the subproblem multiple times. The proposed approach is applied to a mixed integer economic MPC case study on the operation of chemical processes. We show that the proposed algorithm always finds feasible solutions to the optimization problem, given that the mixed integer MPC problem is feasible, and leads to a significant reduction in solution time (up to 97% or 50×) while incurring small error (in the order of 1%) compared to the application of standard and accelerated Generalized Benders Decomposition.

A Review of Robust Machine Scheduling

Robust optimization (RO) has been recognized as an effective means to deal with unanticipated events in highly uncertain and risky environments. This paper systematically reviews two types of emerging RO machine scheduling approaches—robust machine scheduling (R-MS) and distributionally R-MS (DR-MS) methods—which usually offer tractable formulations and analytical results for machine scheduling problems under uncertainty. First, after highlighting the advantages of RO methods over the stochastic approach in terms of tractability and robustness, we use the bibliometric method to analyze the literature related to R-MS/DR-MS problems and classify them from the following aspects: (1) uncertain factors, (2) uncertainty descriptions, (3) robustness criteria, (4) machine environments and (5) solution methods. Second, we discuss the uncertainty descriptions, and the robust feasibility and robust optimality criteria. We further provide a state-of-the-art review of R-MS/DR-MS models in different machine environments and discuss the performance of the R-MS/DR-MS models. Third, we review and discuss the existing exact, approximation, online, and heuristic solution methods for solving R-MS/DR-MS models. Finally, we present future research opportunities in two promising areas: green machine scheduling problems and machine learning-enabled algorithms. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Machine scheduling plays an essential role in industrial and service systems, such as manufacturing, power generation, transportation and medical systems. However, in practice, scheduling systems usually operate in highly uncertain environments due to noisy measurements, prediction errors, and implementation deviations. To ensure robust feasibility and robust optimality, robust machine scheduling (R-MS) and distributionally R-MS (DR-MS) approaches have been recently proposed to hedge against the uncertainties related to processing time, release time, due date, machine breakdown, etc. This paper provides a comprehensive review of the R-MS/DR-MS models and algorithms in different machine environments from the aspects of uncertainty descriptions, robustness criteria and solution methods. This paper further highlights the challenges of R-MS problems and provides promising and valuable research opportunities in terms of problem formulations and algorithm designs.

A Fast Reliability Evaluation Strategy for Power Systems under High Proportional Renewable Energy—A Hybrid Data-Driven Method

With the increasing scale of the power system, the increasing penetration of renewable energy, and the increasing uncertainty factors, traditional reliability evaluation methods based on Monte Carlo simulation have greatly reduced computational efficiency in complex power systems and cannot meet the requirements of real-time and rapid evaluation. This article proposes a hybrid data-driven strategy to achieve a rapid assessment of power grid reliability on two levels: offline training and online evaluation. Firstly, this article derives explicit analytical expressions for reliability indicators and component parameters, avoiding the computational burden of repetitive Monte Carlo simulation. Next, a large number of samples are quickly generated by parsing expressions to train convolutional neural networks (CNNs), and the system reliability index is quickly calculated under changing operating conditions through CNNs. Finally, the effectiveness and feasibility of the proposed method are verified through an improved RTS-79 testing system. The calculation results show that the method proposed in this article can achieve an online solution of second-level reliability indicators while ensuring calculation accuracy.

Global Prescribed Performance Control for Strict Feedback Systems Pursuing Uncertain Target.

In this work, an online solution for reconstructing and predicting the uncertain target trajectory in real-time is proposed based on general regression neural network (GRNN). On this basis, an adaptive tracking control scheme guaranteeing prescribed performance is suggested for a class of strict-feedback systems with unknown control directions. In contrast to existing trajectory reconstruction methods, the one presented in this note does not require prior modeling of the uncertain target or offline training. Contrary to most current state-of-the-art prescribed performance control (PPC) technology, a novel time-varying scaling function and its corresponding translation function are introduced such that no strict constraints on initial conditions are needed, that is, global stability is achieved. The proposed control scheme allows the output of the system to chase the predicted value of the uncertain target, and the tracking error converges to a prescribed small set within a preassigned time, despite unmatched uncertainties and unknown control directions. The benefits of the proposed control scheme are confirmed by numerical simulations.

Legal Issues Involved in Electronic Payments System in India

The Indian economy has developed rapidly after the induction of digital interfaces in commerce, trade, and industry particularly after the popularisation of electronic payment systems or digital banking. Since 2016 when the Government of India announced demonetization, electronic payments have been rising and are expected to continue in the future because the government has promoted these types of payments. Internet penetration in India was 47 percent in 2022 and it was more than 100 percent in urban areas as compared to rural areas, now with the expansion of the information technology-enabled generation which is using digital modes of payments more in their daily transactions has resulted in more than 140 crore rupees each day through various methods of digital prevailing in India. State Governments are also prioritizing and making more efforts to ensure that the unprivileged people should have to be provided access to web services so that they may also make payments conciliatory through this method. Resultantly, there are 103 billion digital transactions worth Indian rupee 166 trillion in the financial year 2023. It is also expected that digital transactions will also rise to 411 trillion by the year 2027. Consequently, on advent of high tech system of fund transfer and its enormous use several cases of fraud have also been taking place on daily basis. The legislation has enacted various laws in connivance with the global laws, to resolve the problem, but they are still prevailing. The present study has been conducted to identify the legal issues and the results arising from these issues and to recommend some pathways to recover from these obstacles. This study further explains the further way to improvement in fund transfer and making payments using digital mode. Consequently, it is found that the present legal system does not have sufficient provisions to stop such fraud, and blockage of money with the UPI, payment gateways, banks, and merchants. There is no single online solution to these problems. The banking ombudsman is working on resolving some of the issues, but due to the red tapism, such transactions of payment failure and fraud websites could not be resolved. Sufficient amendments dealing with such transactions have not been incorporated in the present Consumer Protection Act. Hence, it is recommended that there should be a virtual hearing in the office of the ombudsman as well as in the court of President Consumers Protection.

Development and Application of On‐Line Solution Annealing Process for 304 Austenitic Stainless Steel

After hot rolling, 304 austenitic stainless steel requires a solution annealing treatment to prevent intergranular corrosion and eliminate work hardening effects. Compared to traditional offline processes, on‐line solution annealing offers advantages in terms of cost and time savings. However, both recrystallization behavior and M23C6 carbide precipitation behavior are significantly influenced by the cooling process after rolling, which poses conflicting requirements. This study investigates the precipitation behavior of M23C6 carbides and the recrystallization softening behavior during the continuous cooling process of hot‐rolled samples. The kinetics equations are derived using the Scheil's additivity rule. The temperature profiles in different regions of the plate are studied using finite element analysis. A practical approach for online solution annealing is proposed and applied in industrial testing.

Understanding how online solution–focused hypnotherapy can support the wellbeing of police personnel and treat symptoms of anxiety and depression

Background: The mental health and wellbeing of police personnel has received increased attention over the last 5 years and rates of mental illness amongst employees are high. Anxiety and depression are the most common mental illnesses within the police force, yet little is known about how effective psychotherapeutic interventions are in treating the symptoms of these mental illnesses in police personnel, that is, how many police personnel recover from anxiety and depression after completing a course of psychotherapy. In the psychotherapy outcome literature, recovery rates for anxiety and depression in clinical samples following treatment are low, between 37% and 47%, suggesting similar outcomes can be expected within the police force using current therapy models. Further research into new or unused interventions is therefore needed to improve recovery rates within the police force. Method: This pilot study explored how a new type of psychotherapy, online Solution Focused Hypnotherapy (SFH), can support the wellbeing of police personnel and effectively treat symptoms of anxiety and depression. A quantitative design was used to measure changes in anxiety (GAD-7) and depression (PHQ-9) symptom severity at pre- and post-intervention and measure changes in wellness using a rating scale (Life Wellness Indicator Tool) at the end of each session. Results: A total of 42 police personnel, both officers and staff, participated in the study and 20 qualified SFH therapists delivered the online intervention. The main finding was that 78% of police personnel who completed a course of SFH and started with clinically significant symptoms of anxiety and/or depression had recovered from their illness following the intervention (i.e. scored below 5 on at least one outcome measure). A total of 97.2% of participants achieved ‘wellness’ after the intervention, compared to 19% at pre-intervention and no participants experienced an increase in symptom scores after completing the intervention. Conclusion: Online Solution Focused Hypnotherapy (SFH) can support the wellbeing of both police officers and staff and effectively treat the symptoms of anxiety and depression. Our findings suggest that SFH is an effective, well liked and safe intervention to use within the police force and provides support for more resources into a larger randomised controlled trial.

Online estimation of objective function for continuous-time deterministic systems

We developed two online data-driven methods for estimating an objective function in continuous-time linear and nonlinear deterministic systems. The primary focus addressed the challenge posed by unknown input dynamics (control mapping function) in the expert system, a critical element for an online solution of the problem. Our methods leverage both the learner’s and expert’s data for effective problem-solving. The first approach, which is model-free, estimates the expert’s policy and integrates it into the learner agent to approximate the objective function associated with the optimal policy. The second approach estimates the input dynamics from the learner’s data and combines it with the expert’s input-state observations to tackle the objective function estimation problem. Compared to other methods for deterministic systems that rely on both the learner’s and expert’s data, our approaches offer reduced complexity by eliminating the need to estimate an optimal policy after each objective function update. We conduct a convergence analysis of the estimation techniques using Lyapunov-based methods. Numerical experiments validate the effectiveness of our developed methods.

A Stackelberg Differential Game-based Optimal Fault-tolerant Control Method for Over-actuated Systems

This paper focuses on the optimal fault-tolerant control problem for over-actuated systems with actuator faults. Based on Stackelberg differential game, a novel integrated method is put forward where the optimal High-level motion controller serves as the leader to give the virtual control input, and the optimal Low-level fault-tolerant allocation strategy acts as the follower to allocate the virtual control input to actuators. Adaptive Dynamic Programming is used to realize the online solution of such an integrated method. A numerical simulation is presented to verify its feasibility.

Enhancing Academic Outcomes through an Adaptive Learning Framework Utilizing a Novel Machine Learning-Based Performance Prediction Method

Introduction:E landscapes have been transformed by technological advancements, enabling adaptive and flexible learning through AI-based and decision-oriented adaptive learning systems. The increasing importance of this solutions is underscored by the pivotal role of the learner model, representing the core of the teaching-learning dynamic. This model, encompassing qualities, knowledge, abilities, behaviors, preferences, and unique distinctions, plays a crucial role in customizing the learning experience. It influences decisions related to learning materials, teaching strategies, and presentation styles. Objective: This study meets the need for applying AI-driven adaptive learning in education, implementing a novel method that uses self-esteem (ES), emotional intelligence (EQ), and demographic data to predict student performance and adjust the learning process. Methods: Our study involved collecting and processing data, constructing a predictive machine learning model, implementing it as an online solution, and conducting an experimental study with 146 high school students in computer science and French as foreign language. The aim was to tailor the teaching-learning process to the learners' performance. Results: significant correlations were observed between self-esteem, emotional intelligence, demographic data, and final grades. The predictive model demonstrated a 90 % accuracy rate. In the experimental group, the results indicated higher scores, with an average of 15,78/20 compared to the control group's 12,53/20 in computer science. Similarly, in French as a foreign language, the experimental group achieved an average of 13,78/20, surpassing the control group's 10,47/20. Conclusion: the achieved results motivate the creation of a multifactorial AI-driven adaptive learning platform. Recognizing the necessity for improvement, we aim to refine the predicted performance score through the incorporation of a diagnostic evaluation, ensuring an optimal grouping of learners

Online estimation of PID controllers and plant dynamics via multi‐recursive least squares estimation from closed‐loop I/O data

AbstractThis article proposes an online solution to address the problem of closed‐loop system identification using multiple recursive least squares estimation protocols. Some control systems cannot be analysed in an open‐loop form for stability reasons or the requirement for online control system operation. So, it is necessary to identify plant dynamics and controller parameters based on input–output data from the feedback structure. The presented method identifies real‐time parameters of plant dynamics and controller parameters by utilising a series of recursive least square estimation algorithms that estimate open‐loop data from noisy input–output data measured from the closed‐loop feedback structure. The proposed method can effectively identify abrupt variations in both the controller parameters and plant dynamics. This capability makes it valuable for deployment as a supervisory component, enabling the detection of any faults that may arise in operating systems. Mathematical formulations and theorems are developed, and two numerical case studies are presented to examine the feasibility and performance of the presented closed‐loop system identification protocol.

Interpretable fusion methodology of health indices with an application to industrial turbine cavitation condition monitoring.

Using health indices (HIs) to characterize machine conditions is greatly helpful to prevent machine failures and their subsequent catastrophe. Fusion and interpretation of the main contributions of HIs to machine condition monitoring are still challenging. In this paper, an interpretable fusion methodology of HIs is proposed for machine condition monitoring. The proposed methodology begins with elements of statistical learning for classification, following by an essence of how HIs are fused with their associated linear weights to realize machine condition monitoring. One main contribution of this paper gives a theoretical justification for positive and negative weights of the proposed fusion methodology for understanding their importance for machine condition monitoring and making the proposed methodology physically interpretable. In order to be suitable for two practical situations, in which whether faulty data are available or not, two solutions including an offline solution with healthy and faulty datasets and an online solution with only available healthy datasets are suggested to estimate interpretable weights of the proposed methodology. Finally, industrial turbine cavitation status data collected from our group are used to verify the proposed methodology and show its superiority to two existing popular machine fault diagnosis methods. This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 2)'.

Online trace detection of mercury ions with enhanced fluorescence excitation within metal-lined hollow-core fiber.

In this Letter, we present a portable all-fiber fluorescent detection system based on metal-lined hollow-core fiber (MLHCF) for the ultra-sensitive real-time monitoring of mercury ions (Hg2+). The system employs a rhodamine derivative as the probe. The hollow core of the MLHCF serves as both the flow channel of the liquid sample and the waveguide of the optical path. The metal coating in the intermediate layer between the capillary and the polyimide (PI) coating in the MLHCF provides good light confinement, enhancing the interaction between the sample and the incident light for better fluorescence excitation and collection efficiency. Additionally, further enhancement is achieved by placing an inserted filter along the light path to reflect the excitation light back to the MLHCF. A 3-cm length of MLHCF enables simultaneous excitation of a 40-µL sample volume and collection of most of its fluorescent signal in all directions, thereby significantly contributing to its exceptional sensitivity with a limit of detection (LOD) of 2.3 ng/L. The all-fiber fluorescence-enhanced detection device also shows rapid response time, excellent reusability, and selectivity. This system presents an online, reproducible, and portable solution for the trace detection of Hg2+ and provides a promising way for detecting other heavy metal ions.