Optimal Flow Research Articles

Edge2LoRa: Enabling edge computing on long-range wide-area Internet of Things

Long-Power Wide Area Networks (LPWAN) is a low-cost solution to deploy very-large scale Internet of Things (IoT) infrastructures with minimal requirements following a classic producer/consumer model. Inevitably such deployments will require a shift towards low-latency, distributed and collaborative data aggregation models. The cloud edge computing continuum (CECC) has been proposed as an evolution of the traditional central ultra-high-end processing cloud into a continuum of collaborative processing elements distributed from the cloud to the network edge. Until today, incorporating existing centralized and monolithic LPWAN architectures in the CECC faces multiple security-related implications. We propose Edge2LoRa, a complete secure solution to incorporate LPWAN architectures in CECC enabling faster data processing while reducing the transmission of sensitive data. It improves network performance through data pre-processing, traffic flow optimization, and real-time local analysis. Edge2LoRa gradually transform existing LPWAN deployments into agile and versatile infrastructures that enable the seamless and efficient processing of data throughout the CECC while guaranteeing service continuity and full-backwards compatibility. We implement Edge2LoRa in hardware compliant with the Things Stack and the LoRaWAN v1.0.4 and v1.1. We evaluate the performance in terms of networking and computing resource utilization, quality of service and security. The results provide a clear indication of the improvements to public and private LoRaWAN infrastructures without any disruption or service degradation for existing legacy services. In public LoRaWAN deployments where large-scale IoT data streams drive big data analytics, we demonstrate core network bandwidth usage reductions of up to 90% and data processing latency improvements by a ×10 factor.

Optimal design of greenfield energy hubs in the context of carbon neutral energy supply

This paper proposes a sequential co-optimization (SCO) framework for the design of greenfield energy hubs, aiming to achieve net zero emissions. The SCO framework offers an evolutionary approach to long-term planning and operation, taking into account various evolving factors such as carbon emission policies, technological and economic advancements in energy supply components, changes in land-use, and developments at different stages of the design horizon. The framework ensures that the design of greenfield developments aligns with their evolving characteristics, determining the optimal dispatch flow for firming renewable energy through co-generation and demand flexibility options like smart loads, electric vehicles, and hydrogen-based systems. A sensitivity analysis is conducted to study the impact of emissions, evolving characteristics of greenfield developments, and techno-economic aspects of supply units on the energy hub design. Case studies demonstrate that the proposed design enables large-scale distributed energy systems to meet local energy demand and participate in the electricity market. The SCO framework provides a robust and flexible platform for the correlated optimization of planning and operation of greenfield energy hubs, for advancing towards net zero emissions.

Determination of optimal air supply form on sludge convective drying process: A CFD-DEM study

Convective thermal drying is usually used in sludge dryers, and the air supply forms significantly affect the sludge drying efficiency. In this work, the drying process of multi-layered sludge is numerically simulated using a coupled computational fluid dynamics-discrete element method (CFD-DEM) approach. Better than our previous work, the current CFD-DEM model further considers the dynamic process of humidity within the flow field. Firstly, the CFD-DEM model is validated based on the mechanistic experimental data. Then, extensive numerical simulations are carried out to investigate the two-layered sludge drying process in the dryer, and the effects of two conventional air supply forms (Top-to-Bottom and Bottom-to-Top) as well as a novel air supply form (Side-assist) on the two-phase flow system are discussed. The simulation results provide in detail the dynamic processes of momentum, heat and mass (moisture) in the convective drying system under different working conditions. Following recommendations are presented to facilitate the operation of the dryer: Bottom-to-Top is better for sludge drying and tends to utilize less heat from the heat source compared to the Top-to-Bottom. The drying efficiency can be further improved by supplying the Side-assist with an optimal flow ratio of side-wind to bottom-wind. Numerical results show that the optimal flow ratio is related to the total air volume, the deflection angle and the side-wind temperature. The present study reveals in depth the impact mechanism of the air supply form on the convective thermal drying process of sludge, which contributes to the design and optimization of high-efficiency dryers.

Hydrothermal properties with entropy generation effects on a hybrid nanofluid considering thermal radiation on a stretching/shrinking sheet

Heat transfer efficiency is a significant area of modern research because it is used in a variety of engineering domains, improving the performance of thermal systems such as solar collectors. In this article, a statistical optimization of hybrid nanofluid flow through a stretching/shrinking inclined surface inside the solar-powered ship with entropy generation is investigated by utilizing copper and alumina as a tinny-sized nanomaterial in base fluid water. Copper is also corrosion-resistant with a high thermal conductivity that can be useful in marine environments where salted water and humidity damage the other materials. Coating or a catalyst for solar thermal systems aluminum oxide can be utilized to generate steam or hot water by using the heat coming from the sun. The significance of thermal radiation is considered as the heat source. The developed mathematical model in the form of the partial differential equation is transformed to nonlinear coupled Ordinary Differential Equations (ODEs) by using similarity variables. The reduced equations are solved numerically by applying the shooting algorithm with the bvp4c tool of MATLAB. The surface response methodology is utilized for the statistical optimization of experimental design parameters. The entropy generation rises with the increase of Reynolds number and Brinkmann number. The highest entropy value is found for the Cu-Al2O3/water with λ = 1.0 for Re = 15 and Br = 15. No significant change is reported in the local Nusselt number for changing the Eckert number value. The Response Surface Modeling (RSM) result shows that the experimental input parameter rises with “a factor.”

Analysis and Optimization of Fluid Flow on the Surface of the Prototype Body of Electrical Vehicle Ganesha Diffabilities Using Solidworks Software

Purpose: The aerodynamic aspect is an aspect that takes into account a force caused by the fluid flow shown by the Coefficient of Drag value. This will affect the optimization of performance and energy consumption used. This study aims to modify the standard design of Electrical Ganesha Diffabilities so that a design with a low Coefficient of Drag value considers ergonomic parameters and user comfort to follow the community of people with disabilities. Theoretical Framework: The main theoretical foundation is based on the laws of aerodynamics, which analyze the movement of air around solid objects and its effect on vehicle performance, with a specific emphasis on minimizing drag. The research employs computational fluid dynamics (CFD), a branch of fluid flows. Models and simulations in Solidworks offer a digital environment for improving design aspects to increase aerodynamic efficiency. This theoretical approach focuses on two main objectives: reducing the drag coefficient (CD), which measures resistance caused by shape and surface characteristics, and applying these findings to achieve practical energy savings and enhance vehicle operation specifically designed for individuals with disabilities. The integration of aerodynamic theory and practical application is essential for solving the specific transportation requirements emphasized in the introduction. This alignment with legislation and social objectives aims to provide improved support for the impaired community. Design/Methodology/Approach: This is a numerical method with an R2D2 research model (Reflective, Recursive, Design, and Development) using the 2020 version of Solidworks Software. Solidworks software is known for software that has speed and accuracy in analyzing. Findings: The results of the fluid flow analysis simulation showed that the design of the modified Electrical Ganesha diffabilities vehicle had a Coefficient of Drag value of 0.353 or 35% lower than the standard vehicle value of 0.547. Through expert assessment, the modified design of Electrical Ganesha Diffabilities has received an assessment of 98% with excellent qualifications. Research, Practical & Social implications: The research contributes to the topic of aerodynamic for disability-friendly vehicles, providing a basis for future academic investigations into accessible transportation options. Essentially, the results can immediately impact the development of electric cars that are both more energy-efficient and performance-optimized for those with impairments. This would lead to lower running expenses and improved user-friendliness. From a social perspective, this research emphasizes a dedication to inclusiveness and accessibility, which has the potential to enhance the ability of impaired persons to move around and ultimately enhance their overall well-being. Additionally, it increases awareness among policymakers and manufactures of the significance of incorporating aerodynamic efficiency into the design of assistive devices, hence fostering wider social acceptance and support for this advancement. Originality/Value: The uniqueness and significance of this work stem from its innovative strategy of combining aerodynamic principles with the development of electric cars particularly tailored for those with disabilities-a relatively unexplored field in transportation research. This research examines the E-GADIS vehicle and fills the gap in the current literature on accessible transportation options.

Scaling laws for optimal power-law fluid flow within converging–diverging dendritic networks of tubes and rectangular channels

Flows in dendritic–fractal networks have garnered extensive research attention, but most studies assume a constant tube or channel cross section. In many applications, the cross section of the tube or channel changes as the flow progresses through it, such as the blood flow through the arterial system, which is a prime example of a deformable or non-uniform tree-like network. Heating, ventilation, and air conditioning ductwork also exemplify a tree-like network with varying cross sections. This research investigates power-law fluid flows in the converging–diverging tubes and rectangular channels, prevalent in engineered microfluidic devices, many industrial processes, and heat transfer applications. Power-law fluid flows through linear, parabolic, hyperbolic, hyperbolic cosine, and sinusoidal converging–diverging dendritic networks of tubes and rectangular channels are studied. The flow is assumed to be steady, incompressible, two-dimensional planar, and axisymmetric laminar flow without considering network losses. A theoretical model has been derived to evaluate the flow conductance under network volume and surface-area constraints. The flow conductance is highly sensitive to network geometry. The effective conductance of all networks increases with increasing daughter-to-parent radius ratio before eventually declining. The maximum conductance occurs when a specific radius or channel-height daughter–parent ratio β* is achieved. This value depends on the constraint and vessel geometry, such as tubes or rectangular channels. The optimal flow conditions for maximum conductance in a constrained tube volume network, βmax*=βmin*=N−1/3, while for a constrained tube's surface-area network, βmax*=βmin*=N−(n+1)/(3n+2). This scaling applies to all converging–diverging tube network profiles. Here, βmax*, βmin* are the radius ratios of the daughter–parent pair at the maximum divergent or minimum convergent part of the vessel. N represents the number of branches splitting at each junction, and n is the power-law index of the fluid. Furthermore, the optimal flow scaling for the height ratio in the rectangular channel, βmax*=βmin*=N−1/2α−1/2 for constrained channel volume and βmax*=βmin*=N−1/2α−n/(2n+2) for constrained surface area for all converging–diverging channel networks, respectively, where α is the channel-width ratio between parent and daughter branches. Additionally, at optimal conditions in both the channels and tube network, pressure drops are equally partitioned across each branching level. The results in this work are validated with experiments and existing theories for limiting conditions. This research expands existing design principles for efficient flow systems, previously in the literature developed for uniform vessels, to encompass non-uniform converging–diverging vessels. Additionally, it provides a valuable framework for studying non-Newtonian flows within complex, non-uniform tree-like networks.

Experimental study on flow optimization and thermal performance enhancement of an ultrathin silicon-based loop heat pipe

Excessive heat flux of integrated circuits (ICs) leads to the failure of electronic devices and the consumption of extra energy. Silicon-based loop heat pipe (sLHP) offers a simple, reliable and easily-integrate method for IC thermal management. In this study, the influence of two common wicks (micropillar arrays (MP) wick and microchannel (MC) wick) on fluid flow and performance of sLHP are systematically compared and studied through visual experiment. And two advanced wicks (in-line long rib (IR) wick and staggered long rib (SR) wick) are proposed to further optimize the sLHP. The results show that the fluctuant vapor-liquid interface in MP wick is beneficial to the supplement of working fluid from adjacent flow channel, but it also introduces the uncertainty of flow. The MC wick features the preset flow channel and stable fluid flow but limited heat transfer capacity. Notably, the IR wick and SR wick effectively enhance that capability of supplementing fluid by combining the advantages of the MP wick and MC wick showing better thermal performance. The effective thermal conductivity of SR-sLHP and IR-sLHP is better than that of MP-sLHP and MC-sLHP, with the maximum values of 860 W/(m·K) and 848 W/(m·K), respectively.

Key Parameters Controlling the Performance of Catalytic Self-Pumping Membranes

Previous studies have demonstrated that a membrane coated with Pt and Au on opposing sides will pump liquid through its pores via catalytic reactions of fuels like H2O2. A membrane pore of such a catalytic membrane was studied via 2D axisymmetric modeling, which solved the Poisson-Nernst-Planck-Stokes equations in COMSOL 5.5. We used a validated model from our prior work and varied key parameters, including the pH value, pore radius, porosity, and pore length, to examine their effect on self-pumping flow rates. The results show that the self-pumping flow rate is most sensitive to pore radius and the operating pH value, followed by porosity (pore area fraction) and pore length. The trade-off between increased ionic current and increased ionic strength can be balanced by tuning these parameters, contributing to optimum self-pumping performance. A membrane with a pore radius of 5 μm, porosity of 20%, and pore length of 10 μm obtained an optimum membrane-average flow velocity of 2.6 μm/s when operating under a pH 7 environment, which is an improvement of over 100% over the maximum experimentally demonstrated velocity. The results highlight the potential of utilizing catalytic reactions to manipulate liquid via membranes/microchannels without external power. Guidelines for the design of the catalytic self-pumping membrane/microchannel are proposed at the end.

Numerical study on piezoelectric inkjet with liquid compressibility

A two-dimensional numerical model for a cylindrical piezoelectric inkjet was developed to analyze the ink droplet formation and meniscus behavior, considering the ink compressibility. The propagation of the acoustic pressure wave, which was generated by the piezo actuator, could be simulated by considering the compressibility of the ink. The volume of fluid method was employed for multiphase flow, while the dynamic mesh method was used to implement the piezo actuation. In this study, the key operational parameters of operating voltage, compressibility of working fluid, dwell time of waveform, contact angle, and restrictor dimensions were varied to conduct a comprehensive parametric analysis. The underlying mechanism governing droplet formation could be identified through the analysis of the propagation of successive acoustic pressure waves. Furthermore, the volume fraction and mass flow rate results were used to analyze the jetting performances quantitatively and qualitatively. The mass flow rate results were used to determine the implicit effect of physical properties, such as the viscosity and surface tension, through momentum analysis. The developed model including ink compressibility accurately predicted the behavior of the inkjet jetting and the meniscus motion. In addition, it allows visualization of the internal flow structure and optimization of operating conditions to increase the stability and productivity of inkjet printing.

Integrating experiments with modeling to understand key bacterial taxa dynamics after episodic mixing of a stratified water column

Hydraulic mixing of stratified reservoirs homogenizes physicochemical gradients and microbial communities. This has potential repercussions for microbial metabolism and water quality, not least in dams and hydraulically controlled waters. A better understanding of how key taxa respond to mixing of such stratified water bodies is needed to understand and predict the impact of hydraulic operations on microbial communities and nutrient dynamics in reservoirs. We studied taxa transitions between cyanobacteria and sulfur-transforming bacteria following mixing of stratified water columns in bioreactors and complemented the experimental approach with a biogeochemical model. Model predictions were consistent with experimental observations, suggesting that stable stratification of DO is restored within 24 h after episodic and complete mixing, at least in the absence of other more continuous disturbances. Subsequently, the concentration of S2− gradually return to pre-mixing states, with higher concentration at the surface and lower in the bottom waters, while the opposite pattern was seen for SO42−. The total abundance of sulfate-reducing bacteria and phototrophic sulfur bacteria increased markedly after 24h of mixing. The model further predicted that the rapid re-oxygenation of the entire water column by aeration will effectively suppress the water stratification and the growth of sulfur-transforming bacteria. Based on these results, we suggest that a reduction of thermocline depth by optimal flow regulation in reservoirs may also depress sulfur transforming bacteria and thereby constrain sulfur transformation processes and pollutant accumulation. The simulation of microbial nutrient transformation processes in vertically stratified waters can provide new insights about effective environmental management measures for reservoirs.

Predictive analytics for traffic flow optimization in urban logistics: A transformer-based time series approach.

In this study, we focus on the analysis and prediction of urban logistics traffic flow, a field that is gaining increasing attention due to the acceleration of global urbanization and heightened environmental awareness. Existing forecasting methods face challenges in processing large and complex datasets, particularly when extracting and analyzing valid information from these data, often hindered by noise and outliers. In this context, time series analysis, as a key technique for predicting future trends, becomes crucial for supporting real-time traffic management and long-term traffic planning. To this end, we propose a composite network model that integrates gated recurrent unit (GRU), autoregressive integrated moving average (ARIMA), and temporal fusion transformer (TFT), namely the GRU-ARIMA-TFT network model, to enhance prediction accuracy and efficiency. Through the analysis of experimental results on different datasets, we demonstrate the significant advantages of this model in improving prediction accuracy and understanding complex traffic patterns. This research not only theoretically expands the boundaries of urban logistics traffic flow prediction but also holds substantial practical significance in real-world applications, especially in optimizing urban traffic planning and logistics distribution strategies during peak periods and under complex traffic conditions. Our study provides a robust tool for addressing real-world issues in the urban logistics domain and offers new perspectives and methodologies for future urban traffic management and logistics system planning.

Adaptive control of transportation infrastructure in an urban environment using a real-coded genetic algorithm

The management of urban areas requires the development of an effective strategy for the evolution of transportation infrastructure to ensure the smooth flow of traffic and pedestrians. A crucial component of this infrastructure is the traffic light system, which plays a vital role in traffic control and traffic safety. Improving the efficiency of traffic control systems in intelligent transportation systems (ITS) has a significant impact on a city’s economy. As a result, the cost of fuel for road users can be reduced, and their level of social comfort can be improved, among other benefits. This paper proposes a novel approach to optimizing traffic flows in smart cities, based on the combined use of the genetic optimization algorithm and the ITS simulation model we developed. The proposed method aims to enhance the efficiency of existing traffic control systems and achieve optimal traffic flow patterns, thereby contributing to a more sustainable and efficient urban environment. The optimization algorithm shown here aggregates the objective functions using a simulation model of a real region of the Moscow road network. The model includes intersections, pedestrian crossings and other features that are implemented in the AnyLogic system. The research aims to create a decision-support system for managing urban transport infrastructure. This system will be used to optimize the duration of traffic light phases in order to minimize the time vehicles spend passing through key nodes in the urban road network. It will also optimize pedestrian flow, reducing the impact of traffic on the environment and improving fuel efficiency. By applying this approach, the capacity of the street network can be significantly increased. Additionally, the negative effects of traffic flow on the environment can be reduced by optimizing fuel use and reducing waiting times at intersections managed by traffic lights. The research methodology involves the development of a hybrid evolutionary search algorithm, the creation of a simulation model for transportation and pedestrian flows in the AnyLogic and a series of optimization experiments that demonstrate the effectiveness of the proposed approach when applied to the modeling of complex urban transportation systems.

Estimation of time delay functions for design of traffic systems

Main aim of this research was to apply multiple approaches for the development of time delay functions on three highways in Bahrain, namely; Dry Dock Highway, Arad Highway and Zallaq Highway. Four equations were obtained from previous studies and two equations were, additionally, tailored for each of the three highways. The results were used to obtain two parameters that aid in design, optimum flow rate and level of service.

ANALISIS PERBANDINGAN PRODUKSI SEBELUM DAN SETELAH WELLSERVICE PADA SUMUR X LAPANGAN Y PT PERTAMINA EP

Well X started production on February 9th, 2012 with oil production of 217 BOPD and peak production on March 1th, 2012 with oil production of 2756 BOPD. As production progresses, the reservoir pressure will decrease resulting in a decrease in the production rate. Well X was shut-in on March 7th, 2023 with oil production of 197 BOPD and watercut reaching 91.27%. The location of this study is administratively located in Campurejo Village, Bojonegoro District, Bojonegoro Regency. Analysis of well potential and well forecasting are carried out by the Wiggins method. This method was chosen because the X well has a three-phase fluid and a high water cut. The calculation results show a maximum flow rate of 4111.52 BFPD and an optimum flow rate of 2466.91 BFPD. After calculating the optimum flow rate, and to avoid water cloning, it is recommended that wells be produced with a production flow rate of 2412.54 BFPD at a well base flow pressure (Pwf) of 1368 Psi. Keyword: well service; IPR; future IPR

A Steady-Pressure Control Method for Emulsion Pump Station Based on Online Updating of Optimal Flow Rate

In order to solve the problem of unstable fluid supply pressure and serious impact caused by the complicated and changeable working condition of a fully mechanized mining face in coal mines and the sluggish response of the fluid supply system to the fluid demand for the hydraulic support, a control method based on online updating generalized regression neural network (GRNN) was proposed. Firstly, the simulated hydraulic support test platform and co-simulation model were built. Secondly, The optimal flow dataset of steady-pressure fluid supply under different working conditions is calculated by simulation. Furthermore, the GRNN prediction model was established by using dataset and online updating learning technology to predict the optimal fluid supply flow according to environmental parameters. Finally, the optimal flow control method of online updating GRNN was established, and numerical research and experimental verification were also carried out in different working conditions. The results indicated that the proposed control method could track the working conditions of the working face in real time and adjusted the fluid supply flow of the emulsion pump station adaptively, which effectively alleviated the pressure fluctuation and pressure shock, and the system pressure was more stable, meeting the demand of steady-pressure fluid supply on the working face.

AI optimization framework using digital layouts of array structures: A case study for fuel cells

It is challenging for common artificial intelligence (AI) frameworks to optimize layouts of array structures, because AI is unable to recognize and adjust layouts. To address this challenge, a novel AI optimization framework has been proposed, where layouts of array structures are represented in digital codes to enable AI in layout optimizations. The optimizations of baffle layout and modular channel layout in proton exchange membrane fuel cells are used to validate the methodology. For the multi-objective optimization of baffle layout, although the channel with optimal baffle layout (OC) exhibits a little higher pressure drop than the conventional channel, it increases the net power density and oxygen uniformity by 2.4% and 1.5%, respectively. Consistently, for the multi-objective optimization of channel layout, the optimal flow field with an optimal channel layout (OFF-OC) shows a small increase of pressure drop that can be compensated by the much-enhanced output. So, the net power density of OFF-OC has been elevated by 7.0% in comparison with that of the conventional parallel flow field. Meanwhile, the oxygen uniformity of OFF-OC has also been improved by 4.0%. The simulation results have been verified experimentally. These examples have demonstrated the effectiveness of the AI optimization framework using digital layouts.

Development of an economic and information system for the optimization of city traffic flows

The paper presents a critical analysis of current approaches to reorganizing urban transportation routes. It proposes addressing the problem of optimizing traffic flows as a multidimensional issue encompassing social and economic aspects. An economic-information model for continuous monitoring and optimization of urban traffic flow configurations based on the criterion of congestion wait time has been developed. The calculation of the economic consequences of such waiting time is proposed. The developed system has practical significance and can be applied in managing traffic flows as an economic subsystem of the city within its socio-economic system. Urban transportation infrastructure in Ukraine faces significant challenges due to social changes, including increasing passenger flow, extended waiting times, and the need to adhere to modern urban planning standards. Current trends involve redistributing street and road space based on principles of equal access and safety. This includes pilot actions, intermediate reconstruction, and comprehensive reorganization of urban space and transportation routes. Proposed methods for enhancing transportation infrastructure include improving government management, implementing proactive management strategies, executing investment projects, establishing public-private partnerships, temporarily reducing tax burdens, developing comprehensive solutions for consumers, and optimizing transportation pricing. These strategies aim to address the pressing problems in Ukraine's transport sector and facilitate sustainable development and growth. The study focuses on the financing of infrastructural projects in Dnipro city through the municipal budget. It proposes integrating economic-mathematical models into a unified economic-information system for optimizing traffic flows, allowing for continuous monitoring and improvement. This system emphasizes minimizing congestion wait times and can adapt to dynamic changes in traffic patterns, ensuring efficient and effective urban traffic management. By implementing this system, the city can enhance its transportation network, contributing to overall economic efficiency and better quality of life for its residents.

Bicriteria Nash flows over time

Flows over time are a natural way to incorporate flow dynamics that arise in various applications such as traffic networks. In this paper we introduce a natural variant of the deterministic fluid queuing model in which users aim to minimize their costs subject to arrival at their destination before a pre-specified deadline. We determine the existence and the structure of Nash flows over time and fully characterize the price of anarchy for this model. The price of anarchy measures the ratio of the quality of the equilibrium and the quality of the optimum flow, where we evaluate the quality using two different natural performance measures: the throughput for a given deadline and the makespan for a given amount of flow. While it turns out that both prices of anarchy can be unbounded in general, we provide tight bounds for the important subclass of parallel path graphs.

Improved algebraic inverter modeling for four-wire power flow optimization

This paper discusses the modeling of inverters used in distributed energy resources in steady state. Modeling the interaction between distribution grids and inverter-based resources is crucial to understand the consequences for the network’s operational and planning processes. This work highlights the limitations of existing models and emphasizes the need for better representations of inverters and their control laws in decision-making contexts. Improved steady-state grid-following and grid-forming inverter models are presented, including both three-leg and four-leg converter variants. The advantages of these improved models in mathematical optimization contexts are showcased by investigating the power quality improvement capabilities of the inverters. Numerical studies integrating the proposed inverter models in a four-wire unbalanced optimal power flow engine are presented, and trade-offs between modeling detail and computational intensity are illustrated.

Chance constrained optimal power-water flow: An iterative algorithm assisted by deep neural networks

The optimal power-water flow (OPWF) is a fundamental tool for operating integrated power and water networks. To address uncertainties in renewable energy and load demands, researchers have used chance-constrained models to investigate OPWF under uncertainty. However, existing work has limitations, such as oversimplified network representations, intractable problem formulations, and high computational burdens. This paper presents a chance-constrained OPWF formulation that incorporates detailed network constraints and stochastic uncertainties from wind speeds and electricity/water demands. By leveraging the concept of quantiles of stochastic variables and convexification techniques, the model is recast into a deterministic mixed-integer second-order cone programming (MISOCP) problem with uncertain margins. To efficiently solve this problem, we propose a novel iterative algorithm assisted by deep neural networks (DNNs). The algorithm integrates two DNNs: one designed to solve power and water flow equations, accelerating the probabilistic evaluation of uncertain margins; and the other to predict pipeline flows and refine variable ranges, facilitating a warm-start approach to the MISOCP model. Case studies conducted on the IEEE 123-node feeder coupled with a 67-node water distribution network validate the two DNNs and the overall iterative algorithm. The findings demonstrate that the proposed DNN-assisted approach effectively balances system security and economy. Compared to existing algorithms, the relative error of the optimization solution is less than 0.03%, with a speedup ratio exceeding 200.