Rolling Horizon Optimization Research Articles

Analyzing variability and coordinated demand management for various flexible integrations of residential distributed energy resources

Deploying distributed energy resources (DERs) is crucial for decarbonizing the building sector, but challenges arise due to the energy mismatch between on-site generation and consumption. Impacts of large-scale development of distributed energy technology are seldom evaluated from a system-wide perspective. This study primarily utilizes high-resolution meter data to analyze residential energy consumption behaviors and variability of solar photovoltaics (PV), heat pump and fuel cell throughout the year. Then, rolling horizon optimization is applied to harness demand flexibility through scheduling developed integrated energy systems, considering synergies between on-site energy resources and demand side management. The techno-economic performances of the integrated systems are investigated by adopting wholesale spot prices for PV grid feed-in. Results show that flexible schedule of integrated energy systems can deliver multiple benefits, including energy saving, cost reduction and grid-support interaction, improvement in PV self-consumption through flexible coupling can exceed 40 % compared to the measured results. The effectiveness of demand-side solutions strongly depends on the density and variability of household energy consumption, micro cogeneration presents a greater potential of cost-saving and carbon reduction in winter months. Findings emphasize the importance of coordinated demand management strategy in enhancing effectiveness of energy usage and grid-friendly interactions under widespread DERs implementation.

Distributed cooperative guidance strategy based on virtual negotiation and rolling optimization

The problem of multi-UAV cooperative guidance under target maneuvering conditions is studied, and a distributed cooperative guidance strategy based on virtual negotiation mechanism and rolling horizon optimization is proposed. Firstly, in order to improve the time coordination and guidance control effect at the same time, local coordination variables and objective functions are designed under the rolling horizon optimization framework, and a multi-constrained cooperative guidance optimization model in a limited time domain is constructed; secondly, in order to enhance the robustness of the guidance system to maneuvering targets, a disturbance observer based on nonlinear autoregressive neural network is designed; thirdly, for the control input coupling between UAVs, a virtual negotiation mechanism is proposed to achieve synchronous decision-making and eliminate internal "differences", and the root mean square propagation algorithm of Nesterov momentum is used to design the guidance command generation strategy; finally, digital simulation and semi-physical simulation experiments are carried out respectively. The results show that the proposed guidance strategy can cope with various interferences and improve the cooperative guidance effect through online prediction and optimization, and is expected to be further applied and tested in actual tasks.

An individualized adaptive distributed approach for fast energy-carbon coordination in transactive multi-community integrated energy systems considering power transformer loading capacity

The optimization of multi-community integrated energy systems (MCIES), as a proficient means of integrating distributed energy resources and diverse loads, poses a compelling challenge. This challenge revolves around strategically harnessing the energy-carbon synergy advantages within these systems, while factoring in the heterogeneity among different communities and the constraints imposed by electrical connectivity devices. Facing the challenge, this paper proposes an individualized adaptive distributed approach for energy-carbon coordination in MCIES with power transformers (PT-MCIES). Firstly, a feasible region is constructed based on current and temperature limits to assess the loading capacity of power transformers. Based on this, a transactive energy (TE) based co-optimization model for PT-MCIES considering energy sharing and carbon trading is developed, where rolling horizon optimization is adopted to cope with the randomness from renewable energy and loads. For the TE problem, the alternating direction method of multipliers (ADMM) algorithm is employed to achieve distributed optimization. Uncertain renewable energy and loads, along with variable rolling horizons, make it difficult for the traditional ADMM to ensure convergence speed in the co-optimization of PT-MCIES. Accordingly, an individualized adaptive ADMM (IAADMM) embedded a spectral penalty parameter selection rule is adopted. Simulation results show that the proposed scheduling model can effectively guarantee the safe operation of power transformers with the suggestion of a feasible region, and achieve higher economic and environmental benefits than the reference one that ignores energy-carbon coordination. Furthermore, the proposed IAADMM exhibits superior performance in terms of convergence speed and robustness to the initial penalty parameter when compared to ADMM and its various variants.

Inner-outer layer co-optimization of sizing and energy management for renewable energy microgrid with storage

Conventional microgrid optimization schemes fall short in achieving global optimality for both sizing and scheduling aspects. In response to the demand for simultaneous optimization, this paper presents a novel inner-outer layer framework that includes an outer layer dedicated to sizing optimization and an inner layer focused on Energy Management System (EMS) operational optimization. This approach has a distinctive mechanism of two-layer interaction, where the outer layer focuses on the size assignment and renewal, while the inner layer is constrained by the size assignment and provides feedback on the corresponding operational cost to the outer layer. It enhances the capability of global optimization since the optimal sizes are searched within a fixed space. To establish the range of initial generation values, the framework commences with a pre-optimization phase. Based on the convexity nature of optimization problems, a combined solution methodology involving Rolling Horizon Optimization (RHO) and Particle Swarm Optimization (PSO) is implemented. The case study demonstrates that the algorithm exhibits a good convergence within 30 generations, reaching a global satisfactory solution with a population size of 50. Furthermore, our analysis of optimal sizes across diverse scenarios fills the research gap in understanding the relationship between optimal sizes and operational scenarios. These results underscore that the impact of the time-of-day tariff strategy is significant, and it is risky to determine the optimal sizes by rule-based strategies. Finally, the comparison to other co-optimization methods shows that the proposed framework can reduce the annual total cost by up to 23.1%, which highlights its greater capability of global optimization.

Modified Model Predictive Control for Coordinated Signals along an Arterial under Relaxing Assumptions

This paper proposes modified model predictive control (MMPC) for coordinated signals, aiming to enhance a model’s fidelity to the realistic traffic environment by relaxing typical assumptions. We focus on the arterial, where every intersection is equipped with a dual-ring-barrier signal controller that complies with the standards of the National Electric Manufacturers Association. MMPC employs the store-and-forward model to describe traffic flow, thereby transforming the signal control problem into a model-based rolling-horizon optimization problem, in which the prediction horizon is composed of several future sample intervals, commonly equal to the cycle length. A radar detector is used to collect vehicle data upstream of the stop line at every sampling instant. The optimization problem is solved to minimize the number of vehicles within the prediction horizon, and the next timing plan is determined based on the optimization results. Constraints are added and modified in order to incorporate the typical relaxed assumptions in the optimization process. For this purpose, MMPC introduces a transition-free ring-barrier structure, vehicle distribution ratio, and percent arrival before the end of green. Simulation results indicate that coordination can be maintained by MMPC without the need for transitions, and the estimation of current and future traffic states can be improved with the assistance of modified constraints. Compared with benchmark techniques, MMPC offers superior vehicle progression for coordinated movement and significant improvements in delays, number of stops, and total travel time from a system-wide perspective, with an acceptable small increase in runtime.

Train rescheduling and platforming in large high-speed railway stations

To deal with train delays in large high-speed railway stations, a multi-objective mixed-integer nonlinear programming (MO-MINLP) optimization model was proposed. The model used the arrival time, departure time, track occupation, and route selection as the decision variables and fully considered the station infrastructure layout, train operational requirements, and time standards as limiting factors. The optimization objective was to minimize train delays and reduce track and route adjustments. To realize the large-scale and rapid solution of the MO-MINLP model, this study proposed a rolling horizon optimization algorithm that used “half an hour” as a time interval and solved the rescheduling and platforming problem of each time interval step-by-step. In numerical experiments, 227 train movements under delay circumstances in Hangzhoudong station were optimized by using the proposed model and solution algorithm. The results show that the proposed MO-MINLP model could resolve route conflicts, compress unnecessary dwell times, and reduce train delays; the solution algorithm could efficiently increase the computational speed. The maximum solution time for optimizing the 227 train movements is 15 min 24 s.

Flexible renewable energy planning based on multi-step forecasting of interregional electricity supply and demand: Graph-enhanced AI approach

Jeju Island faces curtailment problems when renewable energy generation exceeds the facility capacity. In addition, the renewable energy system cannot achieve consistent operation because of the uncertainty of renewable energy sources (RES) and their complex spatiotemporal patterns. Climate change and extreme meteorological phenomena also affect the energy system of the island. Therefore, it is essential to maximize RES exploitation to accomplish carbon-free energy production. This study developed a rolling horizon optimization–based flexible renewable energy distribution planning (FxRE-Plan) based on an artificial intelligence-driven spatiotemporal RES prediction model. An adaptive graph convolutional recurrent network (AGCRN) was used to develop a spatiotemporal prediction model. Then, FxRE-Plan was determined using a multiobjective genetic algorithm to maximize the RES potential under climate change scenarios. The FxRE-Plan was evaluated and compared with the current operation of the electric grid in Jeju Island through economic, environmental cost, and climate change vulnerability assessment index. The results of this research show that the AGCRN–based spatiotemporal prediction model exhibited superior prediction performance, achieving a 95% R2. In addition, the FxRE-Plan reduced greenhouse gas emissions by approximately 11.5% at maximum and climate change vulnerability. Hence, the proposed FxRE-Plan can be used to solve curtailments in real electric grids by pursuing carbon-free islands.

Autonomous Planning Algorithm for Satellite Laser Ranging Tasks Based on Rolling Horizon Optimization Framework

Observation task planning is a key issue and the first step in the development of automated Satellite Laser Ranging (SLR) systems. Aiming at the problem of dynamic change of cloud cover during SLR operation, this paper proposes an autonomous mission planning algorithm for SLR based on the Rolling Horizon Optimization (RHO) framework. A hybrid event- and cycle-driven replanning mechanism is adopted, and four functional modules, rolling, planning, information acquisition and decision-making, are established to decompose the SLR observation task planning process into a series of static planning intervals. An improved ant colony algorithm is proposed and utilized to realize the autonomous planning of SLR system observation tasks, and the above autonomous planning algorithm is verified and analyzed based on the SLR system at station 7237. The results show that the above algorithm can effectively increase the number of observation satellites and revenue under cloud disturbance, solve the problems of low efficiency and poor interference resistance of conventional static algorithms, and provide a new research idea for the establishment of an unattended SLR system.

Long-term operation of isolated microgrids with renewables and hybrid seasonal-battery storage

With the progress of decarbonization, renewable-powered microgrids are attracting wide attention. To cope with the fluctuation of renewable power at different timescales, both long-term and short-term energy storage devices are required. This paper studies the operation of renewable-dominated isolated microgrids integrated with hybrid seasonal-battery storage. A data-driven scheduling-correction framework is proposed. By leveraging the historical data of renewable power and load, the scheduling module generates ex-post optimal state-of-charge (SoC) sequences of the seasonal energy storage ahead of the operating year. In each period of real-time operation, the correction module performs two steps: the first step is to update the reference SoC for the seasonal storage based on the ex-post optimal SoC sequences and the newly observed data; the second step is to solve a bi-objective rolling-horizon optimization problem which minimizes the instant operating cost while steering the SoC of seasonal storage to its reference value. An appealing feature of the proposed method is that the long-term renewable power forecasts are not required. A microgrid system is devised to verify the proposed framework. Numerical tests show that the scheduling-correction framework outperforms existing rolling horizon approaches in compromising economy, power supply reliability, and renewable energy utilization.

Rolling Horizon Based Temporal Decomposition for the Offline Pickup and Delivery Problem with Time Windows

The offline pickup and delivery problem with time windows (PDPTW) is a classical combinatorial optimization problem in the transportation community, which has proven to be very challenging computationally. Due to the complexity of the problem, practical problem instances can be solved only via heuristics, which trade-off solution quality for computational tractability. Among the various heuristics, a common strategy is problem decomposition, that is, the reduction of a large-scale problem into a collection of smaller sub-problems, with spatial and temporal decompositions being two natural approaches. While spatial decomposition has been successful in certain settings, effective temporal decomposition has been challenging due to the difficulty of stitching together the sub-problem solutions across the decomposition boundaries. In this work, we introduce a novel temporal decomposition scheme for solving a class of PDPTWs that have narrow time windows, for which it is able to provide both fast and high-quality solutions. We utilize techniques that have been popularized recently in the context of online dial-a-ride problems along with the general idea of rolling horizon optimization. To the best of our knowledge, this is the first attempt to solve offline PDPTWs using such an approach. To show the performance and scalability of our framework, we use the optimization of paratransit services as a motivating example. Due to the lack of benchmark solvers similar to ours (i.e., temporal decomposition with an online solver), we compare our results with an offline heuristic algorithm using Google OR-Tools. In smaller problem instances (with an average of 129 requests per instance), the baseline approach is as competitive as our framework. However, in larger problem instances (approximately 2,500 requests per instance), our framework is more scalable and can provide good solutions to problem instances of varying degrees of difficulty, while the baseline algorithm often fails to find a feasible solution within comparable compute times.

Rolling horizon optimization based real-time energy management of a residential neighborhood considering PV and ESS usage fairness

The incorporation of decentralized energy solutions, including solar photovoltaic (PV) installations and energy storage systems (ESSs), into residential communities has received substantial interest in recent times. This is driven by the objective of enhancing the self-reliance of residential zones while decreasing their reliance on centralized power grids. Effective management of these systems can yield advantages such as load equalization, cost reduction, and diminished emissions. The process of optimizing energy management in residential communities entails addressing multiple factors, including uncertainty, equity, and efficiency.This study introduces an innovative methodology for real-time energy management in a residential community, taking into account both the equitable utilization of solar PV and ESS and the minimization of costs. The suggested technique employs rolling horizon optimization and mixed-integer linear programming (MILP) to tackle uncertainties in PV production and guarantee a fair allocation of shared resources. The outcomes of this novel approach showcase its capability to sustain cost-effectiveness while fostering equitable energy consumption.

Co-optimization of decarbonized operation of coal-fired power plants and seasonal storage based on green ammonia co-firing

Coal-fired power plants (CFPP) can provide significant inertia and flexibility support for power systems with a high share of renewable energy (RE). The ammonia–coal co-firing technology can effectively reduce carbon emissions (CE) from CFPP. We propose a low-carbon power supply and multi-timescale energy storage system in combination with this technology. The system consists of batteries, fuel cells and the CFPP equipped with the ammonia–coal co-combustion module. It can also cope with short and long term fluctuations in RE. We use the Mixed Integer Linear Programming method to construct an optimization model for this system. We then set up six sub-cases according to the power systems in Texas, USA. Based on weekly and annual simulations of these cases, we analyze the economic and environmental performances of the proposed system with different RE shares, as well as exploring the characteristics of different energy storage methods. Compared to batteries or fuel cells only scenarios, CFPP configured with green ammonia co-firing can significantly reduce the total operating cost (TOC), CE and RE curtailment. We use the rolling horizon optimization method to simulate and calculate the distribution of ammonia storage levels throughout the year. The ammonia storage levels are high in spring and autumn and low in summer. Finally, the sensitivity and efficiency analysis of the proposed system is carried out. As far as ammonia co-firing technology allows, the higher the maximum ammonia–coal mixing ratio, the lower TOC, CE and RE curtailment. This phenomenon is more significant at a higher RE share. The overall efficiency of green ammonia synthesis and combustion for power generation is around 13.92%. It can work in synergy with batteries and fuel cells to improve efficiency and reduce the marginal cost of long-term energy storage.

Provision of multiple services with controllable loads as multi-area thermal energy storage

Power systems are experiencing a decrease of synchronous generation along with increased penetration of inverter based renewable generation leading to reduced system inertia and a need for flexible resources. Non-generating resources such as thermostatically controlled loads (TCLs) are flexible due to their thermal energy storage capacity. When aggregated, TCLs can arbitrage energy prices and provide reserves to the power system. We approach the operational flexibility of the TCLs by modeling a risk-averse aggregator that controls decentralized TCLs and aims to maximize its own profit. The high number and low power rating of residential TCLs makes it difficult to model and assess their flexibility potential on national level. Thus, we make use of a high-level thermal energy storage model for aggregations of TCLs to quantify their flexibility potential. We present a method to aggregate temperature, TCL parameters, and building stock data into a thermal battery equivalent. We propose a multi-period multi-market multi-zonal two-stage chance constrained rolling horizon optimization problem formulation for the risk-averse day-ahead self-scheduling problem of a price-taker TCL aggregator bidding in energy and reserve markets under uncertainty and recast the problem as a linear program. We perform several case studies in the Swedish power system based on a survey of single- and two-family dwellings with electric heating and assess the flexibility potential. Additionally, a sensitivity analysis provides insights regarding market design and policy implications.

A reliable emergency logistics network for COVID-19 considering the uncertain time-varying demands

The evolving COVID-19 epidemic pose significant threats and challenges to emergency response operations. This paper focuses on designing an emergency logistic network, including the deployment of emergency facilities and the allocation of supplies to satisfy the time-varying demands. A Demand prediction-Network optimization-Decision adjustment framework is proposed for the emergency logistic network design. We first present an improved short-term epidemic model to predict the evolutionary trajectory of the epidemic. Then, considering the uncertainty of the estimated demands, we construct a capacitated multi-period, multi-echelon facility deployment and resource allocation robust optimization model to improve the reliability of the decisions. To address the conservativeness of robust solutions during the evolution of the epidemic, an uncertainty budget adjustment strategy is proposed and integrated into the rolling horizon optimization approach. The results of the case study show that (i) the short-term prediction method has higher accuracy and the accuracy increases with the amount of observed data; (ii) considering the demand uncertainty, the proposed robust optimization model combined with uncertainty budget adjustment strategy can improve the performance of the emergency logistic network; (iii) the proposed solution method is more efficient than its benchmark, especially for large-scale cases. Moreover, some managerial insights related to the emergency logistics network design problem are presented.

Two-Timescale Dynamic Energy and Reserve Dispatch With Wind Power and Energy Storage

The integration of volatile renewable resources and energy storage entails making dispatch decisions for conventional coal-fired units and fast-response devices in different timescales. This paper studies intraday dynamic energy-reserve dispatch following a two-timescale setting. The coarse timescale determines the hourly reference output and reserve allocation, which offers a sufficient backup for the fine-timescale operation; the fine timescale determines the adjustment of gas-fired units and energy storage system every 15 minutes in response to the actual wind power. A stochastic dynamic programming method is proposed to make decisions at the coarse timescale while guaranteeing the robust feasibility of the fast process via vertex scenarios of uncertainty set and bounding the state-of-charge intervals for energy storage; the fast-response actions at the fine timescale are updated using a truncated rolling-horizon optimization, which incorporates the cost-to-go functions calculated at the coarse timescale to prevent the fast decisions from being myopic. Case studies on the modified IEEE 5-bus system and 118-bus system validate the proposed framework.

High-power electric vehicle charging: Low-carbon grid integration pathways with stationary lithium-ion battery systems and renewable generation

The energy transition in the mobility sector is well underway. The electrification of road transport is resulting in a shift of the energy demand from the oil and gas sector to the electricity grid. Increasingly aggressive targets for low charging times for Electric Vehicles (EVs) are slated to raise the demand for High-Power Charging (HPC). This is likely to lead to bottlenecks and overloading in vulnerable sections of the electricity grid. Battery Assistance (BA) is a promising grid integration measure for High-Power Charging (HPC) to mitigate these problems. As decarbonization is the primary objective of the energy transition, the determination and comparison of the Global Warming Potential (GWP) footprints for HPC stations with BA is crucial. A comprehensive mathematical framework for the modelling and quantification of GWP footprints for HPC has been developed. The Levelized Emissions of Energy Supply (LEES) methodology has been extended and generalized to handle energy from the grid. A new state variable for the Battery Energy Storage System (BESS) — the State of Carbon Intensity (SOCI) has been introduced to calculate the operation phase GWP footprint of the BESS. The energy consumption GWP footprint for the load is also described by a new quantity — the Load Energy Consumption (LEC) emissions. The effect of incorporation of local Photovoltaic Solar (PV) generation in the energy flows is also investigated. An optimized Energy Management System (EMS) strategy with rolling horizon optimization to minimize emissions has been implemented to regulate energy flows in scenarios with BA and local PV generation. The Levelized Emissions of Energy Supply (LEES) values are obtained for all simulated scenarios and compared against a baseline rule-based EMS strategy. In combination with on-site PV generation, BA could achieve a reduction of 24% in the LEES vis-á-vis the baseline strategy. For reference, two scenarios with Grid Reinforcement (GR) for the grid section with and without local PV generation have also been simulated. With Grid Reinforcement (GR), a reduction of over 2% can be achieved with respect to the baseline EMS strategy for BA. Grid Reinforcement (GR) in conjunction with local PV generation can bring about a further reduction of about 6% with respect to the baseline EMS strategy for BA.

Event-trigger rolling horizon optimization for congestion management considering peer-to-peer energy trading among microgrids

This paper designs an event-trigger rolling horizon optimization framework to alleviate electricity congestion caused by peer-to-peer (P2P) energy transactions among microgrids (MGs) under uncertainty. This framework incorporating abounded time dimensions includes three processes: first, a discrete-time linear programming model for the P2P energy trading among MGs with real-time data updating for reaction to underling uncertainties, are formulated to derive initial schemes in prediction time windows; second, a modified optimal power flow model is used to verify congestion in control time windows, with congestion occurrence defined as an event; third, the power rescheduling of MGs is triggered by this event for reducing periodic calculation burden and executed to generate new trading schemes for congestion alleviation in control time windows. We develop an online distributed optimization algorithm to realize independent decisions of MGs and guarantee rolling updates of system parameters through embedding alternating direction method of multipliers into every time window. Finally, simulations in different cases are implemented to illustrate the reasonability and effectiveness of the proposed optimization framework. Results show that congestion is reasonably managed while ensuring the diversity of P2P energy transactions. Compared with the period-driven rolling horizon optimization framework, the computational time is significantly reduced in the proposed framework.

Real-Time Holding Control for Transfer Synchronization via Robust Multiagent Reinforcement Learning

This study presents a robust deep reinforcement learning (RL) approach for real-time, network-wide holding control with transfer synchronization, considering stochastic passenger demand and vehicle running time during daily operations. The problem is formulated within a multi-agent RL framework where each active trip is considered as an agent, which not only interacts with the environment but also with other agents in the considered transit network. A specific learning procedure is developed to learn robust policies by introducing <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$maxmin$ </tex-math></inline-formula> optimization into the learning objective. The agents are trained via deep deterministic policy gradient algorithm (DDPG) using an extended actor-critic framework with a joint action approximator. The effectiveness of the proposed approach is evaluated in a simulator, which is calibrated using data collected from a transit network in Twin Cities Minnesota, USA. The learned policy is compared with no control, rule-based control and the rolling horizon optimization control (RHOC). Computational results suggest that RL approach can significantly reduce the online computation time by about 50% compared with RHOC. In terms of policy performance, under deterministic scenario, the average waiting time of RL approach is 1.3% higher than the theoretical lower bound of average waiting time; under stochastic scenarios, RL approach could reduce as much as 18% average waiting time than RHOC, and the performance relative to RHOC improves when the level of system uncertainty increases. Evaluation under disrupted environment also suggests that the proposed RL method is more robust against short term uncertainties. The promising results in terms of both online computational efficiency and solution effectiveness suggest that the proposed RL method is a valid candidate for real-time transit control when the dynamics cannot be modeled perfectly with system uncertainties, as is the case for the network-wide transfer synchronization problem.

Rolling horizon optimization for real-time operation of prosumers with Peer-to-Peer energy trading

Peer-to-Peer energy trading is recognized as a promising approach for prosumers to improve the operational economics. However, the uncertainty of renewable energy poses challenges to the reliable and economical operations of prosumers. This paper focuses on the real-time operation of prosumers. An efficient rolling horizon optimization-based real-time operation strategy for prosumers is proposed to minimize the total operational cost in one-day, in which the thermal comfort demand of the prosumers is also considered. The case study is finally conducted for 94 prosumers located at an urban community microgrid in a typical summer day scenario. Simulation results show that the proposed rolling horizon operation strategy can make full use of the flexible energy resources of prosumers, realizing the local energy supply–demand balance while improving prosumers’ operational economics. Moreover, the negative impact of day-ahead forecasting errors on the intra-day operation can be reduced significantly.

Tri-level hybrid interval-stochastic optimal scheduling for flexible residential loads under GAN-assisted multiple uncertainties

Various building loads, such as heating, ventilation, and air conditioners (HVACs), electric water heaters (EWHs), and electric vehicles (EVs), can introduce opportunities for improving the flexibility of electricity consumption while satisfying the needs of building owners as well as benefiting the resilience of distribution system. To utilize such flexibility, a tri-level distribution market framework is established, including residential consumers, load aggregators (LAs), and the distribution system operator (DSO). The uncertainties from all three levels are considered. The random consumption behavior at the consumer level is modeled as a Gaussian noise that is also aggregated and transmitted to the LA level. The weather temperature in the LA level is forecasted as an interval, and the photovoltaic (PV) power in the market-clearing level is modeled by a set of power scenarios generated by Generative Adversarial Networks (GANs). Then, a hybrid interval-stochastic programming is proposed to transform the uncertain problems in the first two levels into deterministic ones. For real-time implementations, a rolling horizon optimization (RHO) scheme is employed to continuously optimize the power consumption based on the latest operating information. Finally, case studies on a modified IEEE 69-bus system validate the effectiveness of the proposed uncertainty modeling strategies and the RHO scheme.