Multi-objective Optimal Scheduling Research Articles

Multi-objective genetic algorithm embedded with reinforcement learning for petrochemical melt-flow-index production scheduling

In the petrochemical industry, product type conversion can cause capacity loss and produce transition products, leading to waste. Our study aims to minimize these transition products and tardiness in meeting customer due dates. We introduce the Engineering Experience Heuristic (EEH), which utilizes scheduling reference sheets to identify key production traits and constraints, thereby generating efficient schedules. Further building on the EEH, we propose a non-dominated sorting genetic algorithm II enhanced with reinforcement learning (NSGAeRL) to address the multi-objective scheduling optimization problem. The incorporation of reinforcement learning (RL), particularly through a model-based Markov Decision Process (MDP), allows for the dynamic adjustment of genetic algorithm (GA) parameters, including crossover and mutation mechanisms, based on the optimal policy derived from RL. We validate our proposed methodologies through empirical studies and numerical experiments. The results demonstrate that NSGAeRL outperforms standard benchmarking algorithms, offering superior performance in minimizing transition products and scheduling tardiness.

Multi-Objective Optimal Scheduling of Microgrids Based on Improved Particle Swarm Algorithm

Microgrid optimization scheduling, as a crucial part of smart grid optimization, plays a significant role in reducing energy consumption and environmental pollution. The development goals of microgrids not only aim to meet the basic demands of electricity supply but also to enhance economic benefits and environmental protection. In this regard, a multi-objective optimization scheduling model for microgrids in grid-connected mode is proposed, which comprehensively considers the operational costs and environmental protection costs of microgrid systems. This model also incorporates improvements to the traditional particle swarm optimization (PSO) algorithm by considering inertia factors and particle adaptive mutation, and it utilizes the improved algorithm to solve the optimization model. Simulation results demonstrate that this model can effectively reduce electricity costs for users and environmental pollution, promoting the optimized operation of microgrids and verifying the superior performance of the improved PSO algorithm. After algorithmic improvements, the optimal total cost achieved was CNY 836.23, representing a decrease from the pre-improvement optimal value of CNY 850.

Multi-objective optimization scheduling method considering flexible load integration for distribution network

In response to a series of issues in the distribution network, such as inadequate and inflexible utilization of flexible loads, delayed response to demand participation, and the uncertainty of new energy source output, a differentiated objective-based method for optimizing distribution network operations is proposed. Firstly, flexible loads are categorized, and corresponding mathematical models are established. Secondly, by employing chance-constrained programming to account for the uncertainty in new energy source output, a multi-objective optimization model is developed to reduce distribution network economic costs, decrease network losses, and enhance power supply reliability. Subsequently, an improved NSGA-III algorithm is introduced to address the multi-objective model. Finally, an 11-node distribution network is used as a case study, and three different algorithms are comprehensively compared. This confirms the rationality of the optimized scheduling scheme proposed in this paper.

Reinforcement Learning-Based Multi-Objective Optimization for Generation Scheduling in Power Systems

Multi-objective power scheduling (MOPS) aims to address the simultaneous minimization of economic costs and different types of environmental emissions during electricity generation. Recognizing it as an NP-hard problem, this article proposes a novel multi-agent deep reinforcement learning (MADRL)-based optimization algorithm. Within a custom multi-agent simulation environment, representing power-generating units as collaborative types of reinforcement learning (RL) agents, the MOPS problem is decomposed into sequential Markov decision processes (MDPs). The MDPs are then utilized for training an MADRL model, which subsequently offers the optimal solution to the optimization problem. The practical viability of the proposed method is evaluated across several experimental test systems consisting of up to 100 units featuring bi-objective and tri-objective problems. The results demonstrate that the proposed MADRL algorithm has better performance compared to established methods, such as teaching learning-based optimization (TLBO), real coded grey wolf optimization (RCGWO), evolutionary algorithm based on decomposition (EAD), non-dominated sorting algorithm II (NSGA-II), and non-dominated sorting algorithm III (NSGA-III).

Modeling and multi-objective optimization for energy-aware scheduling of distributed hybrid flow-shop

With the development of economic globalization and sustainable manufacturing, energy-aware scheduling of distributed manufacturing systems has become a research hot topic. However, energy-aware scheduling of distributed hybrid flow-shop is rarely explored. Thus, this paper is the first attempt to study an energy-aware distributed hybrid flow-shop scheduling problem (DHFSP). We formulate a novel mathematical model of the DHFSP with minimizing makespan and total energy consumption (TEC) criteria. A hybrid multi-objective iterated greedy (HMOIG) approach is proposed to address this energy-aware DHFSP. In this proposed HMOIG, firstly, a new energy-saving method is presented and introduced into the model for reducing TEC criterion. Secondly, an integration initialization scheme is devised to produce initial solutions with high quality. Thirdly, two properties of DHFSP are used to invent a knowledge-based local search operator. Finally, we validate the effectiveness of each improvement component of HMOIG and compare it with other well-known multi-objective evolutionary algorithms on instances and a real-world case. Experimental results manifest that HMOIG is a promising method to solve this energy-aware DHFSP.

Multi-objective optimization scheduling and flexibility margin study in integrated energy systems based on different strategies

Integrated Energy Systems (IES) serve as an effective solution to address grid fluctuations. However, mainstream IES still adhere to established supply strategies such as thermal and electrical non-conversion (TENC), heat determined by power (HDP), and power determined by heat (PDH). These strategies overlook the additional flexibility generated by the synergy between electricity and heat, preventing the full realization of their advantages in supporting the grid. This paper proposes a Flexible Scheduling (FS) operational strategy for IES that maximizes the utilization of flexibility resources to meet the demands of heating, cooling, and electricity while maintaining grid stability. The superiority of this strategy is analyzed through an IES multi-objective optimization scheduling model and a comprehensive flexibility margin model. The results of a case study indicate that the FS strategy reduces total costs by 19.9% compared to TENC, 16.6% compared to HDP, and 5.2% compared to PDH. It exhibits the strongest support for the grid, increasing the overall flexibility margin of IES by 40.5% compared to TENC, 12.7% compared to HDP, and 8.2% compared to PDH. The FS-based IES operational strategy proposed in this paper contributes significantly to the flexible and economical operation of IES.

Research on the Quantitative Evaluation of the Three-Dimensional Seismic Resilience of Power Systems Based on an Improved Genetic Algorithm

ABSTRACT In this study, a three-dimensional (3D) performance function is established to evaluate 3D seismic resilience, and a multiobjective optimization scheduling model based on node importance and repair order evaluation indicators is developed. On the basis of sequential coding, considering the number of repair teams, the concept of a “repair team vector” is proposed, and an improved genetic algorithm based on the Pareto dominance relationship and an elite file strategy is introduced to screen for the optimal postearthquake repair scheduling scheme. The results demonstrate that the developed optimization scheduling model yields improved computational accuracy and speed in the case evaluations.

Multi objective optimization scheduling of unmanned warehouse handling robots based on A star algorithm

SummaryThe sorting efficiency of the warehouse management and handling robots (automated guided vehicles [AGVs]) in an unmanned warehouse affects the delivery and lead time of orders. Studying the collaborative sorting of multiple AGVs can significantly improve work efficiency. The goal of this paper is to minimize the overall shortest transportation path and time while ensuring the completion of all orders and corresponding recycling or return tasks. This paper conducts experiments on global path planning for multiple AGVs based on the A* algorithm, both without considering collision and deadlock situations, and considering collision and deadlock situations. The results show that without considering collision and deadlock situations, the method of matching fixed storage locations and picking stations can improve overall efficiency, while considering collision and deadlock problems will result in reduced efficiency. In the future, the model will be further optimized taking into account actual conditions to improve overall efficiency.

Short-term optimization scheduling method of cascade hydropower and photovoltaic complementary system based on pumping station operation strategy

With the rapid development of photovoltaic power generation, how to improve the photovoltaic grid connection rate is an urgent problem to be solved. This article proposes an optimized scheduling method for the water and photovoltaic complementary system, taking into account the operation strategy of pump stations to improve the photovoltaic grid connection rate. Firstly, a multi-objective optimization scheduling model is constructed to consider both power generation and output fluctuation, and the uncertainty of photovoltaic power generation is analyzed from multiple perspectives. Then, taking the cascade hydropower stations and surrounding photovoltaic power stations in a river basin in Sichuan as an example, the operation strategy of pump stations is introduced into the water and photovoltaic complementary system, considering different weather scenarios, to reduce the photovoltaic curtailment rate. The study verifies that the introduction of pump stations can effectively increase the photovoltaic grid connection rate, and quantitatively analyzes the pump station capacity configuration under different photovoltaic penetration rates.

Intelligent learning-based cooperative and competitive multi-objective optimization for energy-aware distributed heterogeneous welding shop scheduling

This research is focused on addressing the energy-aware distributed heterogeneous welding shop scheduling (EADHWS) problem. Our primary objectives are to minimize the maximum finish time and total energy consumption. To accomplish this, we introduce a learning-based cooperative and competitive multi-objective optimization method, which we refer to as LCCMO. We begin by presenting a multi-rule cooperative initialization approach to create a population that combines strong convergence and diversity. This diverse population forms the foundation for our optimization process. Next, we develop a multi-level cooperative global search strategy that explores effective genes within solutions from different angles and sub-problems. This approach enhances our search for optimal solutions. Moreover, we design a competition and cooperation strategy for different populations to expedite convergence. This strategy encourages the exchange of information and ideas among diverse populations, thereby accelerating our progress. We also introduce a multi-operator cooperative local search technique, which investigates elite solutions from various directions, leading to improved convergence and diversity. In addition, we integrate Q-learning into our competitive swarm optimizer to explore different regions of the objective space, enhancing the diversity of the elite archive. Q-learning guides the selection of operators within the small-size population, contributing to more efficient optimization. To evaluate the effectiveness of LCCMO, we conduct numerical experiments on 20 instances. The experimental results unequivocally demonstrate that LCCMO outperforms six state-of-the-art algorithms. This underscores the potential of our learning and knowledge-driven evolutionary framework in enhancing performance and autonomy when it comes to solving EADHWS.

Consideration of Multi-Objective Stochastic Optimization in Inter-Annual Optimization Scheduling of Cascade Hydropower Stations

There exists a temporal and spatial coupling effect among the hydropower units in cascade hydropower stations which constitutes a complex planning problem. Researching the multi-objective optimization scheduling of cascade hydropower stations under various spatiotemporal inflow impacts is of significant importance. Previous studies have typically only focused on the economic dispatch issues of cascade hydropower stations, with little attention given to their coupling mechanism models and the uncertainty impacts of inflows. Firstly, this paper establishes a coupled optimization scheduling model for cascade hydropower stations and elaborates on the operational mechanism of cascade hydropower stations. Secondly, according to the needs of actual scenarios, two types of optimization objectives are set, considering both the supply adequacy and peak-shaving capacity as indicators, with the total residual load and the peak-valley difference of the residual load as comprehensive optimization objectives. Subsequently, considering the uncertainty impact of the inflow side, a stochastic optimization model for inflow is established based on a normal distribution probability. Finally, case study analyses demonstrate that the proposed model not only effectively achieves supply stability but also reduces the peak-valley difference in load, and can achieve optimized scheduling under the uncertain environment of inflow.

Multi-objective optimal scheduling considering low-carbon operation of air conditioner load with dynamic carbon emission factors

As global temperatures rise and climate change becomes more severely. People realize that air conditioning systems as a controllable resource and play an increasingly important role in reducing carbon emissions. In the past, the operation optimization of air conditioning systems was mainly oriented to user comfort and electricity costs ignoring the long-term impact on the environment. This article aims to establish a multi-objective model of air-conditioning load to ensure user temperature comfort performance and reduce the total cost (i.e., electricity cost and carbon emission cost) simultaneously. Multi Sand Cat Swarm Optimization (MSCSO) algorithm combined with gray target decision-making (GTD) is used to explore optimal solution. Meanwhile four competitive strategies are applied to validate the effectiveness of the proposed method, i.e., genetic algorithm (GA), MSCSO-comfort objective, MSCSO-total electricity cost objective and unoptimization. The simulation results show that the MSCSO-GTD based objective method can significantly reduce total costs while taking into account appropriate indoor temperature comfort.

An Improved Multi-Objective Brain Storm Optimization Algorithm for Hybrid Microgrid Dispatch

The increasing integration of renewable energy sources into microgrids has led to challenges in achieving daily optimal scheduling for hybrid alternating current/direct current microgrids (HMGs). To solve the problem, this article presents a novel hybrid AC/DC microgrid scheduling method based on an improved brain storm optimization (BSO) algorithm. Firstly, with economic and energy storage device health as the primary objective functions, this paper proposes a dispatch model for AC-DC hybrid microgrids. To overcome the limitations of traditional algorithms, including premature convergence and can only find non-inferior solution sets, this article proposes a multi-objective BSO algorithm that integrates learning and selection strategies. Additionally, a fuzzy decision-making method is employed to achieve optimal daily dispatching and select the most suitable compromise solution. Finally, experiments are conducted to verify the effectiveness of the proposed multi-objective optimal scheduling method and to demonstrate the practicality and effectiveness of the method in real application scenarios.

Multi-objective particle swarm optimization for optimal scheduling of household microgrids

Addressing the challenge of household loads and the concentrated power consumption of electric vehicles during periods of low electricity prices is critical to mitigate impacts on the utility grid. In this study, we propose a multi-objective particle swarm algorithm-based optimal scheduling method for household microgrids. A household microgrid optimization model is formulated, taking into account time-sharing tariffs and users’ travel patterns with electric vehicles. The model focuses on optimizing daily household electricity costs and minimizing grid-side energy supply variances. Specifically, the mathematical model incorporates the actual input and output power of each distributed energy source within the microgrid as optimization variables. Furthermore, it integrates an analysis of capacity variations for energy storage batteries and electric vehicle batteries. Through arithmetic simulation within the Pareto optimal solution set, the model identifies the optimal solution that effectively mitigates fluctuations in energy input and output on the utility side. Simulation results confirm the effectiveness of this strategy in reducing daily household electricity costs. The proposed optimization approach not only improves the overall quality of electricity consumption but also demonstrates its economic and practical feasibility, highlighting its potential for broader application and impact.

Long-term multi-objective optimal scheduling for large cascaded hydro-wind-photovoltaic complementary systems considering short-term peak-shaving demands

The effective synergy among hydropower, wind power, and photovoltaic enhances variable renewable energy (VRE) utilization. However, existing long-term hydropower operating rules that consider runoff uncertainty neglect escalating peak-shaving demands. This paper optimizes the long-term decision-making of hydropower by supplementing the demand to buffer short-term VRE uncertainty. Latin hypercube sampling and K-means clustering reduction are utilized to generate coupling scenario sets to quantify long-term runoff and short-term VRE uncertainties. Then, a double-layer multi-objective optimization model is developed, the outer layer maximizes the long-term expected energy production of the whole system, and the inner layer minimizes hourly residual load fluctuation of power grids under daily electricity boundaries. The daily electricity is dependent on the load profile and monthly generation. Moreover, A power-electricity coupling approach is proposed to bridge long- and short-term operations and reduce the computational burden. An optimal set of pareto solutions is finally obtained with different constraint boundaries, where a compromise solution is selected by a fuzzy decision method. The model has been implemented on the Lancang River hydro-wind-photovoltaic complementary system in Southwest China. The results indicate that: (1) the model can transfer hydropower electricity from flood season to dry season, facilitate VRE integration, increase overall benefits, and improve short-term hydropower regulation capacity, especially in wet years; (2) the obtained Pareto solution set has significant advantages. Under multi-year average conditions, energy production increases by 11 million kWh, hydropower curtailment decreases by 751 million kWh, and residual load fluctuations reduce by 2200 MW, and (3) increasing transmission capacity is more conducive to improving system efficiency in wet years than in dry years, and is helpful to enhance hydropower flexibility.

Enhanced Multiobjective Optimization Algorithm for Intelligent Grid Management of Renewable Energy Sources

Optimal scheduling of microgrids (MGs) is a crucial component of smart grid optimization, playing a vital role in minimizing energy consumption and environmental degradation. However, existing methods tend to consider only a single optimization and do not consider the multiobjective optimization problem of MGs in a comprehensive and integrated way. This study proposes a comprehensive multiobjective optimal scheduling methodology for renewable energy MGs, incorporating demand-side management (DSM) considerations. Initially, a DSM multiobjective optimization model is formulated, focusing on the load shifting of controllable devices within the MG to refine the electricity consumption structure. This model contemplates the renewable energy consumption of the MG, customer electricity purchase costs, and load smoothness. Subsequently, a multiobjective optimization model for grid-connected MGs, encompassing wind and photovoltaic power generation, is constructed with the dual objectives of economic and environmental optimization for the MG. Ultimately, a multimodal multiobjective optimization algorithm, amalgamating a local convergence index and an environment selection strategy, is proposed to solve the model. The experimental results show that compared with other methods, the proposed method in this paper can reduce the integrated cost by 32.6% and 38.9% in summer and 19.4% and 40.2% in winter. This stands out as a unique contribution in the field of MG optimization, as it integrates DSM considerations into a multiobjective optimization model. This methodology achieves a balance between minimizing energy consumption and environmental degradation while also enhancing economic efficiency.

Multi energy complementary optimization scheduling method for wind solar energy storage and charging integrated energy system

Abstract IES (The Integrated Energy System), consisting of distributed wind and solar power generation and multiple types of loads for cooling, heating, and electrical systems, is an important application scenario in the current energy configuration. It is not possible to balance multiple objectives like economy, carbon emissions, and wind and solar energy curtailment. Furthermore, there are numerous equipment that have multiple energy flows, complex conversion processes, and multiple scheduling requirements. Therefore, multi-objective optimization and minute-level scheduling strategies are key technologies to improve the utilization efficiency of comprehensive energy systems. This article proposes a comprehensive method for optimizing and scheduling energy systems that is based on multi-objective optimization and multi-time scale decomposition. Firstly, a comprehensive energy system architecture for wind solar storage and charging was constructed, and its operational characteristics were analyzed. Then, a multi-objective optimization scheduling model was established, which comprehensively considered multiple objectives such as system operating cost, minimum carbon emissions, and minimum wind and solar curtailment rate. Through time scale decomposition, the optimization scheduling problem was transformed into multiple subproblems and solved separately. Finally, it was verified through a case study. The simulation results show that the constructed model reduces the total operating cost by 5%, the wind abandonment rate by 7%, and the carbon emissions by 5.6% compared to the system without energy storage and charging piles. This verifies the effectiveness of the constructed model, reduces the system operating cost, and reduces the impact on the environment; compared with the DA-P (Day Ahead Programming), the proposed optimization method reduced the system’s electricity purchase cost by 7.51%, increased renewable energy utilization by 11%, and reduced carbon emissions by 6.1%. This verifies the feasibility of the proposed method in reducing system operating costs, improving system environmental protection, and stabilizing the system.

A multi-objective segmentation scheduling method for the flexible dismantling of retired power batteries taking into account transfer time

Decommissioned power batteries are prone to dilapidated deformation, which makes it difficult to carry out unified and efficient production scheduling for disassembly production. In this paper, a multi-objective scheduling method applied to the dismantling workshop of retired power batteries is presented. For the characteristics of power battery dismantling, a strategy of scheduling by a battery pack and battery module in stages is proposed. The multi-objective optimal scheduling model of the dismantling workshop is established with the decision objectives of reducing the time of completion, energy dissipation and workstation load, taking into account the transfer time of batteries in the dismantling process, and is solved by genetic algorithm. The chromosome coding method, the crossover variation method and the elite retention strategy in the genetic algorithm were optimized. The method is applied to the dismantling examples of 5 kinds of power batteries, and the simulation results show that the proposed method is feasible and effective.

An advanced multi-objective collaborative scheduling strategy for large scale EV charging and discharging connected to the predictable wind power grid

With the large-scale EV connected into the wind power grid, the intermittent, fluctuating and stability bring rigorous challenges for power quality and dispatch, thus wind curtailment becomes more serious. This paper proposes an advanced multi-objective collaborative scheduling strategy to improve the accuracy of the predictable wind grid and ensure the stable operation of the grid by optimizing wind power and EV synergistically. Firstly, a hybrid power prediction method is proposed based on density-based spatial clustering applied to noise (DBSCAN) and partial least squares regression (PLSR) combined with long and short-term memory neural network (LSTM). It establishes a linear component prediction mode to predict the nonlinear wind power efficiently. Secondly, a multi-objective optimization scheduling model is established according to the predicted wind power, considering the vehicle-to-grid (V2G) characteristics of EV, grid load fluctuations, wind curtailment capacity, EV charging costs, and grid losses. The global control aims to achieve overall energy balance and optimize the charging and discharging of EV in a time dimension under constrained conditions. Additionally, based on the total number of EV charging and discharging determined by the global level control, a spatial scheduling optimization is conducted for EV and wind power by the distribution network control, with the goal of minimizing network losses in the distribution network system. Finally, through simulation and comparison of four scenarios, the results demonstrate that the proposed method achieves synergistic optimization of wind power and EV. This paper provides an efficient solution for the optimized scheduling of large-scale EV connected to the predictable wind power grid.

Multi-objective global dynamic optimal scheduling of smart building loads considering carbon emissions

In recent years, there has been a significant increase in electricity consumption and carbon emissions from households in smart buildings. This increase has had a profound impact on the economic aspects of residential electricity consumption and the achievement of the national dual carbon goal. In this paper, an optimal scheduling model for household loads in smart buildings is established. It considers the user demand side, grid-side supply, and the impact of the PV energy storage system (PESS) on carbon emissions. The optimization objectives are the economy of household electricity consumption and the total deviation of electricity consumption. Second, the adaptive mixed inverse learning strategy multi-objective beluga optimization algorithm (AMOBWO) is adopted to enhance its overall dynamic optimization. This optimization addresses challenges such as the uneven distribution of electricity consumption, load timing constraints, power limitations, and uncertainty in electricity consumption during the scheduling of smart building loads. Finally, the results demonstrate that AMOBWO decreases the total cost of household electricity consumption in smart buildings by 59.32% (based on the selected maximum PV capacity). Additionally, it reduces the total deviation by 14.28% after optimal scheduling. As the PESS capacity increases, there is a significant reduction in the indirect carbon emissions from smart buildings, decreasing from 881.279 kg CO2 to 431.299 kg CO2.