Operation Strategy Research Articles

Multi-region coupling computational fluid dynamics simulation of the underground compressed air energy storage process

Compressed air energy storage (CAES) in underground spaces is a common method for addressing the instability of renewable energy generation. As the construction and testing of CAES systems are often of high cost, the numerical simulation which offers a more efficient and low-cost research method can provide a better alternative to research the process. In this study, a numerical simulation model has been developed to describe the air movement within the CAES process. Specifically, the study focuses on two different types of motion: air compressible flow within the cavern and air porous flow in the surrounding rock. Using OpenFOAM, a multi-region coupling solver has been developed to address the different governing equations for these two types of motion, and couples pressure, velocity, and temperature at the boundaries. The developed solver is used to simulate a field test of a CAES system. The numerical simulation results closely match the experimental data, verifying the reliability of the solver. Moreover, the solver can achieve multi-region flow simulations that are previously unattainable, resulting in more accurate simulations. Simulations have also been conducted to analyze various working conditions, including different rock permeability, porosity, and air injection mass rates. The results show that different conditions significantly affect air pressure, leakage rate, temperature, and flow field changes within the cavern. These simulation results and the underlying mechanisms have been analyzed to provide reference and technical support for site selection, construction, and operational strategies of CAES systems in underground spaces.

Optimizing CO2 Capture Efficiency: Harnessing IoT and Industry 4.0 for Precise Temperature Analysis in Packed Absorption Columns

The deployment of various technologies to mitigate climate change is crucial for developing techniques that advance climate action. Climate change is exacerbated by rising levels of carbon dioxide (CO2) and other greenhouse gases, deforestation, and the use of fossil fuels. Urgent measures are needed to enhance CO2 capture efficiency, in alignment with the Sustainable Development Goals (SDGs) and climate action initiatives. This study investigates the influence of temperature variations in a packed absorption column on CO2 capture efficiency. By employing Internet of Things (IoT) and Industry 4.0 principles, it facilitates precise data acquisition to monitor temperature fluctuations during experiments. Comparative evaluations under steady-state and saturation conditions provide critical insights for optimizing CO2 capture in post-combustion processes. Conducting exploratory analyses enhances system understanding and informs design and operational strategies for effective and sustainable CO2 capture. This research delves into the technical aspects of temperature optimization, emphasizing its significance for sustainable practices and the urgency of addressing climate change through innovative, technology-driven solutions.

An universal energy-matching design and regulation method for combined cooling, heating, and power (CCHP) systems in different scenarios

In this study, the impact of the coupling matching mechanism between the systems and the users on the energy-saving characteristics of the systems was analyzed based on a universal representation and computation method to identify the energy saving potential of the systems. The physical model was detailed derived for the relationship between the load supply and user demands under different capacity design modes and operation strategies to construct a universal coupling matching diagram, and the impact of the coupling matching parameters (operational energy efficiency, load matching degree, etc) on system integration and operation in different energy use scenarios was quantitative analyzed to illustrate the inherent mechanism of energy saving characteristics. In addition, the coupling mechanism between the systems and the users from a global perspective was reconstructed, and a coupling method of capacity design factor and dual source regulation was proposed to realize the collaborative integration of centralized energy supply systems, combined cooling, heating, and power systems and load demands, as well as the active regulation of the internal cascade utilization of the systems, so as to improve the energy saving potential of the systems under all operating conditions. Finally, a case analysis and method verification were conducted using typical summer days at Kunming hotel as an example. The results show that the coupling matching relationship is the internal mechanism that affects the energy saving of the systems, and the average energy saving rate of the whole day can be increased by 7.45% through collaborative integration and active regulation.

Investigation on the hydraulic loss in the vertical inlet and outlet of a pumped storage power station

Abstract The vertical inlet/outlet is commonly adopted in the upper reservoir of pumped-storage power stations, in which the internal flow patterns exert a critical influence on the safety and operational efficiency of the entire power station. Based on the standard k-ε turbulence model coupled with the revised wall roughness theory, this investigation presented a numerical model of a vertical inlet/outlet in a pumped-storage upper reservoir and the validity and accuracy of the numerical simulation are validated through comparison well with the results of the model experiments. The results suggest that the emergence of vortices of varying intensities near the inlet during power-generation scenarios at dead water levels and at 3.5 times of the rated flow rate (389.6 m3/s). The bend section experiences fairly nonuniform flow velocity, with the highest average flow hydraulic loss in the entire vertical pipe inlet/outlet system. These insights provide a substantial utility for operational strategies and optimization designs in related engineering projects.

Analysis of the influence of brake pipe pressure gradient on heavy haul combined train and optimisation of operation strategy

In this paper, based on the theory of gas flow, the action logic of the control valve, and the principle of multi-rigid-body dynamics, a simulation model of the 20,000 t heavy haul combined train is established to investigate the influence of brake pipe pressure gradient on the braking performance, longitudinal dynamics, braking and release characteristics of trains. Utilizing real railway line conditions, locomotive and vehicle parameters, and train operation monitoring equipment (LKJ) record data of Shuozhou-Huanghua Railway, the cyclic braking condition of the train on the long and steep downhill is simulated, and the control strategy of reducing the coupler force during the cyclic braking is proposed. The results indicate that a larger brake pipe pressure gradient before braking leads to weaker braking capability, and higher coupler forces during braking, but smaller coupler forces during release. As the brake pipe pressure gradient before braking increases, braking synchronicity decreases, while release synchronicity slightly improves. By adjusting the locomotive’s electric braking force during the cyclic braking, it is possible to appropriately increase the brake pipe pressure gradient before braking, effectively reducing coupler forces during release and reducing the number of braking cycles, thus lowering the operational difficulty of the train.

Energy Consumption Optimization for the Cold Source System of a Hospital in Shanghai-Part I: Analysis of Operating Characteristics and the Control Strategies of the Chillers

Background: Hospitals account for the most proportion of energy consumption in the public building sector. Chillers usually account for most of the overall energy consumption of the cold source system. Objective: To solve the problem of chillers' large energy consumption problem, novel technologies were developed, and achievements were patented. Methods: The operating characteristics influencing factors of the magnetic suspension centrifugal chiller (MSCC) and variable frequency screw chiller (VFSC) of a hospital in Shanghai were analyzed and discussed by actual measurements. Then, based on the operating characteristics of the chiller obtained from the analysis of the measured data, the cooling capacity was classified by the K-Means clustering method to obtain the startup strategy of the chillers. Results: The effects of the supply chilled water temperature, the supply cooling water temperature and variable cooling water flow rate on the maximum cooling capacity and coefficient of performance (COP) of both chillers were explored. The load distribution scheme was discussed based on the chillers' startup strategy. Conclusion: The average part load ratio operation scheme was the preferred chiller distribution scheme. A chiller's maximum allowable part load ratio should not exceed 80% during the low-load operation period and should not be less than 60% during the conventional operation period. It provided a reference for optimizing the chiller operation strategy to reduce system energy consumption.

Performance evaluation of composite phase change materials with varying expanded graphite content in a drawer-type latent heat storage tank

The poor thermal conductivity of single-component phase change materials (PCMs) significantly impacts the operational efficiency of solar combi-systems. There is still a gap in the research on the heat release behavior of composite phase change materials (CPCMs). Therefore, this study investigated the heat release behavior of a self-developed drawer-type heat storage tank by varying the content of expanded graphite (EG) in the CPCMs used in it. Simulation was carried out using COMSOL Multiphysics 6.1, followed by experimentation on a test bench. The average outflow temperature, effective energy conversion (EEC), and heat release rate were used to evaluate the performance of the tanks. Comparing the simulation with experimental results, a maximum error of 8.75 % was obtained, indicating the accuracy of the study. The results indicate that adding EG can significantly improve the thermal conductivity of CPCM, with superior heat release behavior observed when the mass fraction of EG reaches 5 %. Under similar temperatures, the average outflow temperature from a 5 % EG tank is approximately 4.4 °C higher, EEC is 84 % higher, and heat release rate is 1.63 times higher than that from an ordinary thermal tank. Under different temperatures in a 5 % EG tank, increasing by 5 °C results in an average outflow temperature increase of 4.1 °C, EEC increase by a factor of one and an increase in heat release rate by 36 %. This study provides valuable insights for subsequent research on operation strategies for solar combined systems.

Two-stage low-carbon economic dispatch of an integrated energy system considering flexible decoupling of electricity and heat on sides of source and load

Under the goal of "double carbon", in order to further enhance the level of new energy consumption and solve the problem of restricting the flexibility of the system by "ordering power by heat" of combined heat and power (CHP) units, a low-carbon economic planning strategy with flexible decoupling of electricity and heat is proposed, by introducing a new type of electric-thermal coupling equipment on both sides of the source and load. Firstly, Consideration of the low-carbon and environmentally friendly characteristics of green ammonia production and ammonia-doped combustion technologies, a wind power(WT) – power to ammonia(P2A) - CHP units - thermal power (TH) units joint operation strategy is proposed on the source side. This strategy realizes the conversion of abandoned wind to green ammonia to ammonia coal hybrid generation, the decoupled operation of CHP units and promotes the consumption of wind power and the low-carbon operation of the system. Secondly, A dynamic incentive demand response model is developed to meet the demand of high proportion distributed PV in situ consumption on the load side. The dynamic incentive price guides the distributed power-to-heat load to change the response capacity, tracks the abandonment of wind and light, realizes the flexible conversion of power and heat load, and cooperates with the source side to promote the coupling operation of electric pyrolysis. On this basis, consider the flexible decoupling capability of electric-heat coupling equipment on both sides of the source and load to establish a two-phase low-carbon scheduling model for the day-before and day-after phases. In the day-ahead phase, the source-side electric-thermal-ammonia joint operation strategy is considered, and the electric and thermal energy supply plans are adjusted centrally; In the intra-day phase, the flexible adjustment range of power-to-heat devices and the heat load inertia on the load side are taken into account, and the electricity and heat planning strategies are adjusted in a distributed-centralised manner in conjunction with the source side. Finally, through the simulation of different cases, the results show that compared with the traditional electric heating system, the total cost of the system considering the scheduling strategy proposed in this paper decreases by ￥826,900, the carbon emission decreases by 1.2t, and basically realises the consumption of wind power and distributed photovoltaic power output. The proposed scheme reduces carbon emissions, promotes the consumption of wind power and distributed photovoltaic output, and is able to reach the goal of low-carbon economic dispatch.

A low-impact nature-based solution for reducing aquatic microplastics from freshwater ecosystems

Effective nature-based solutions (NBS) and strategies for freshwater microplastic (MP) pollution are beneficial for reducing ecological and human health risks. This study proposed an innovative NBS for the in-situ retention of aquatic MPs. By evaluating the tolerance and MP retention efficiency of different submerged macrophytes, Myriophyllum aquaticum was identified as a well-suited system for optimization as NBS for operational MP retainment practice. The response surface method and artificial neural network modeling were applied to determine the optimal operational strategy of this solution, which was determined to be at a flow rate of 60 L/h, aeration intensity of 5 m3/(m2·h), and plant density of 190 plants/m2. Under this strategy, an average MP retention of 93.38% was achieved for the actual tested lake. The retention of MPs was particularly effective for particle sizes larger than 100 μm (especially films and fragments) and for the 4 polymer types. At the same time, also total nitrogen and phosphorus levels in the treated waters were reduced by 80.0% and 78.4% respectively, reflecting the added environmental value for water purification. This NBS provides a feasible strategy for mitigating MP pollution, but further research is needed on its long-term applicability and potential ecological effects in a wider range of specific environments, and effective development of plant harvesting cycle strategies is also essential to achieve long-lasting MP pollution removal.

Techno-Economic Optimization of Microgrid Operation with Integration of Renewable Energy, Hydrogen Storage, and Micro Gas Turbine

Microgrids are integral to modern energy systems, yet they face substantial challenges in integrating diverse components, managing complex dynamics, and ensuring stability amid renewable energy variability. This study investigates the integration of wind turbines, an electrolyzer, and a hydrogen-compatible micro gas turbine (MGT), with a focus on enhancing operational efficiency and maintaining dynamic equilibrium within the microgrid. The synergy between the electrolyzer and MGT provides a robust energy storage solution, improving both system stability and performance.Using advanced machine learning and real operational data, this research generates highly accurate, rapid models with greater precision and detail than conventional methods. The intelligent management system developed combines real-time optimization and adaptive fine-tuning, using forecasts of weather, electricity prices, and energy demand to devise optimized operational strategies. The study systematically analyzes various configurations, including grid-connected and island modes, and evaluates the impact of hydrogen storage in each scenario.The results demonstrate that the optimization approach substantially enhances economic returns. However, this can also lead to increased natural gas consumption and emissions, revealing a trade-off between financial gains and environmental sustainability. This highlights the necessity for strategies that reconcile economic incentives with sustainability objectives, offering valuable insights for improved microgrid management.

Optimal operation strategy for renewable power plants based on 5G base stations response

Abstract The integration of large-scale new energy sources has led to a significant challenge in electricity supply and demand balancing within the power system. To address this issue, it is crucial to establish an optimization strategy of renewable power plant based on 5G base stations response. Firstly, according to the operating state of the base station, the energy storage schedulable strategy of the base station was designed. Then, through the regulation function of the base station’s reserve energy storage and the operation principle of the renewable energy power plant, the operation model of the renewable power plant considering the base station’s participation and response was established. Finally, evaluation indexes such as the absolute peak-to-valley difference, the standard deviation of daily load and the peak-valley difference rate can be used to measure system optimization results. The results show that the proposed strategy improves the source load imbalance in the power system while enhancing reliability and economy of new energy.

Continuous and multicyclic sorption-based atmospheric water harvesting with heat recovery in arid climate

Nowadays, two-thirds of the global population are grappling with water scarcity. Sorption-based water harvesting (SAWH), which does not depend on conventional water sources and provides decentralized clean water, is steadily gaining popularity. However, the contradiction between the low daily water production in arid climates and the high energy consumption of large-scale devices has become a pivotal limitation for efficient water harvesting. Here, we report a multicyclic SAWH device with heat recovery equipped with 3 sorbent beds that alternatively desorb in automatic switching mode to achieve all-day continuous water harvesting. Furthermore, based on the rapid sorption and desorption kinetics of the adsorbent in the initial stages, employing a rapid-cycling operation strategy contributes to realize an outstanding water productivity of 8.07 kg day−1 and 0.21 kg kgsorbent−1 day−1 under practical arid conditions (15 °C/25 % RH). Besides, the apparatus equipped with heat regenerator showed a significant decrease in energy consumption from 12.17 kWh to 10.65 kWh during a desorption cycle (4 h). Moreover, a hybrid desorption mode driven by a combination of solar collector and electric heater is demonstrated in an island. This SAWH system is anticipated to provide a promising approach for large-scale efficient water harvesting in all-day arid regions (RH<35 %).

Optimal economic operation of smart home devices based on home microgrids and time-of-use tariffs

Abstract In this paper, a two-layer model is proposed for smart devices in a home energy management system in order to optimize residential energy use under time-of-use tariffs and home microgrids. Home smart devices are modelled based on their power consumption attributes and building thermal resistance. An HVAC-transferable device cooperative operation strategy is introduced to construct the economic optimization of the upper-level HVAC operation and the lower-level transferable device operation. This strategy reduces home power costs while maintaining user comfort. By iteratively solving the two-layer model, the optimal power consumption scheme for home smart devices is determined.

Direction-dependent Effects on Global 21 cm Detection

Cosmic dawn represents a critical juncture in cosmic history when the first population of stars emerged. The astrophysical processes that govern this transformation need to be better understood. The detection of redshifted 21 cm radiation emitted from neutral hydrogen during this era offers a direct window into the thermal and ionization state of the Universe. This emission manifests as differential brightness between spin temperature and the cosmic microwave background. The SARAS experiment aims to detect the sky-averaged signal in the frequency range 40–200 MHz. SARAS’s unique design and operational strategy to float the antenna over a water body minimizes spectral features that may arise due to stratified ground beneath the antenna. However, the antenna environment can be prone to configuration changes due to variations in critical design parameters such as conductivity and antenna tilt. In this paper, we connect the variations in antenna properties to signal detection prospects. By using realistic simulations of a direction- and frequency-dependent radiation pattern of the SARAS antenna and its transfer function, we establish critical parameters and estimate bias in the detectability of different models of the global 21 cm signal. We find a correlation between the nature of chromaticity in antenna properties and the bias in the recovered spectral profiles of 21 cm signals. We also find stringent requirements for transfer function corrections, which can otherwise make detection prospects prohibitive. We finally explore a range of critical parameters that allow robust signal detection.

Adaptive Operation Strategy of a District Cooling System with Chilled Water Storage and Its Validations by OpenModelica Modeling and Simulations

Developing operation strategies for district cooling systems with chilled water storage is challenging due to uncertain fluctuations of cooling demand in actual operations. To address this issue, this paper developed an adaptive operation strategy and performed its validations by modeling and simulating a commercial cooling system in Shanghai using OpenModelica. Firstly, the originally designed operation strategy of the cooling system was evaluated by simulation but was found unable to meet the statistically averaged ideal cooling requirements due to the early exhaustion of stored chilled water at about 5:30 PM. Then, to build foundations for adaptive operation strategy development, a newly designed operation strategy was established by increasing the operation time of base load chillers in the valley and flat electricity price periods. The new strategy proved numerically sustainable in satisfying the ideal cooling demand. Moreover, to realize the strategy’s adaptability to actual cooling load fluctuations, an adaptive operation strategy was developed by tracking the target stored chilled water mass curve that was calculated by implementing the newly designed strategy. The simulation results verify that the adaptive operation strategy enables good adaptability to representative cooling load fluctuation cases by automatically and periodically adjusting the operation status of base load chillers. The adaptive operation strategy was then further widely numerically tested in hundreds of simulation cases with different cooling load variations. The time-lagging problem resulting in strategy failures was found in numerical tests and was addressed by slightly modifying the adaptive strategy. Results indicate that the adaptive operation strategy enables adaptability to deal with cooling demand fluctuations as well as allowing low cooling supply economic costs and power grid-friendly characteristics. This study provides theoretical support to strategy design and validations for district cooling system operations.

Sustainable Operation Strategy for Wet Flue Gas Desulfurization at a Coal-Fired Power Plant via an Improved Many-Objective Optimization

Coal-fired power plants account for a large share of the power generation market in China. The mainstream method of desulfurization employed in the coal-fired power generation sector now is wet flue gas desulfurization. This process is known to have a high cost and be energy-/materially intensive. Due to the complicated desulfurization mechanism, it is challenging to improve the overall sustainability profile involving energy-, cost-, and resource-relevant objectives via traditional mechanistic models. As such, the present study formulated a data-driven many-objective model for the sustainability of the desulfurization process. We preprocessed the actual operation data collected from the desulfurization tower in a domestic ultra-supercritical coal-fired power plant with a 600 MW unit. The extreme random forest algorithm was adopted to approximate the objective functions as prediction models for four objectives, namely, desulfurization efficiency, unit power consumption, limestone supply, and unit operation cost. Three metrics were utilized to evaluate the performance of prediction. Then, we incorporated differential evolution and non-dominated sorting genetic algorithm-III to optimize the multiple parameters and obtain the Pareto front. The results indicated that the correlation coefficient (R2) values of the prediction models were greater than 0.97. Compared with the original operation condition, the operation under optimized parameters could improve the desulfurization efficiency by 0.25% on average and reduce energy, cost, and slurry consumption significantly. This study would help develop operation strategies to improve the sustainability of coal-fired power plants.

Dynamic Simulation and Performance Analysis of Alkaline Water Electrolyzers for Renewable Energy-Powered Hydrogen Production

This paper presents a comprehensive study on the dynamic simulation modeling of alkaline water electrolyzers. Detailed experimental testing and characteristic analysis reveal that alkaline water electrolyzers have long startup times, rapid dynamic responses, and poor dynamic stability. These characteristics are critical for the development of accurate models and effective strategies. A dynamic simulation model was established in MATLAB R2022b and Simulink, enabling standalone simulation operation and module encapsulation. This model facilitates the construction of hydrogen production clusters and serves as a foundational tool for system strategy research. Simulations of rated current loading and unloading for four electrolyzers over 6 h showed significant differences in startup and operation. Key parameters such as cell voltage, maximum loadable power, hydrogen production efficiency, and energy consumption were analyzed. Temperature simulations indicated significant differences in thermal equilibrium points and cooling modes among the electrolyzers, as determined by structural design and cooling system efficiency. These findings highlight the need for efficiency improvements in high-current density electrolyzers. Overall, the model effectively represents commercial electrolyzer characteristics and offers a reliable tool for future research on control strategies for adapting hydrogen production systems to renewable energy power fluctuations, laying a solid foundation for the optimization of electrolyzer design and operation strategies.

Return-Temperature Reduction at District Heating Systems: Focus on End-User Sites

This review presents a comprehensive examination of recent advancements and findings related to return-temperature reduction in District Heating (DH) systems, with a focus on enhancing overall system efficiency at end-user sites. The review categorizes and clarifies various return-temperature reduction techniques, emphasizing aspects such as building energy performance, heat emitters, thermostatic radiator valves, and substation units. One shall note that return temperature is not a parameter that can be directly controlled within a DH system; instead, it is influenced indirectly by adjusting various system parameters throughout the design, commissioning, operation, and control phases. Key insights include the direct impact of heat demand on return temperatures; the pivotal role of indoor heating systems in optimizing thermal energy use in relation to heat demand; the significance of thermostatic radiator valves in regulating heat output and maintaining low return temperatures; the advantages of ventilation radiators and add-on fans in enhancing radiator efficiency; the necessity for effective substation operation to improve system cooling capacity; and the critical role of operational control strategies in achieving optimal system performance. These findings underscore the need for integrated approaches in DH system design and operation to achieve lower return temperatures and improve overall system efficiency.

Damage Control Orthopaedics Induced Less Trauma-Induced Coagulopathy than Early Total Care in a Porcine Polytrauma Model

Introduction: Coagulopathic disorders (CDs) complicate treatment in polytraumatised patients. Against this background, operative strategies for fracture management are controversial in this cohort. This study therefore investigated the effects of two established operative concepts, early total care (ETC) and damage control orthopaedics (DCO), on CD in a large-animal polytrauma (PT) model. Methods: Twenty-two animals (Sus scrofa domesticus) sustained PT involving blunt-chest trauma, liver laceration, bilateral femur fracture, and pressure-controlled haemorrhagic shock. After resuscitation, animals were allocated to ETC (n = 8), DCO (n = 8), or served as a non-traumatised control group (CG, n = 6). Animals were ventilated and monitored under ICU standards for 72 h. Blood samples were collected at baseline and post-trauma after 1.5, 2.5, 24, 48, and 72 h. Plasminogen activator inhibitor-1 (PAI-1) and thrombin-antithrombin (TAT) complex concentrations were determined by ELISA. Results: Compared to the CG, ETC and DCO subjects had significantly increased plasma concentrations of PAI-1 after 2.5 h (CG vs. ETC: p = 0.0050, CG vs. DCO: p = 0.0016). Furthermore, the ETC group showed significantly increased plasma PAI-1 concentrations after 24 h compared to the CG and DCO groups (CG vs. ETC: p = 0.0002, DCO vs. ETC: p = 0.0004). During the later clinical course, concentrations of TAT were significantly increased in the ETC group compared to the CG and DCO group after 72 h (CG vs. ETC: p = 0.0290, DCO vs. ETC: p = 0.0322). Conclusion: PT is strongly associated with CD in the early post-traumatic course. In comparison to DCO, ETC appeared to be negatively associated with CD. Future studies must investigate this impact, especially in those patients admitted with trauma-induced coagulopathy, to improve outcomes.

Strategic investments in mobile and stationary energy storage for low-carbon power systems

The main feature and trend of the distribution system is the integration of renewable energy with high penetration rates. The variability and zero marginal cost characteristics of renewable energy will lead to drastically fluctuating locational marginal prices. In the deregulated electricity market, merchants have incentives to utilize energy storage and price arbitrage. Mobile energy storage has a short capital payback period and is widely recognized for transferring energy in the temporal and spatial dimensions. This paper analyses the interaction between merchants and distribution system operators and presents a hybrid energy storage strategic investment framework using bi-level programming. In the upper-level problem, the merchant formulates the capacity, location, and operation strategy of different energy storage to maximize the market revenue of hybrid energy storage, which is paid for by the locational marginal price. In the lower-level problem, the distribution system operator develops an optimal dispatch strategy considering renewable energy and merchant investments. A joint energy and reserve market clearing procedure is performed to derive the locational marginal prices. In the lower-level problem, a data-driven solution strategy based on machine learning is introduced. It uses deep neural networks to approximate the mapping relationship between distribution system states and locational marginal prices. The presented methodology is implemented in an IEEE-33 node system. The results demonstrate that, compared to the basic case, the hybrid energy storage investment strategy has led to an 8.1 % increase in merchant profits and a 12.9 % reduction in the operational costs of the distribution network. The deep neural network approximator fully avoids the lower-level problem with less than 5 % optimality loss.