Tomohiro Hayashida
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Tomohiro Hayashida has a total of 55 co-authors. Here are the top co-authors by number of shared publications:
- Shinya Sekizaki
Graduate School of Advanced Science and Engineering, Hiroshima University, Higashihiroshima 739-8527, Japan
21 shared publications - Ichiro Nishizaki
Graduate School of Advanced Science and Engineering, Higashihiroshima Campus, Hiroshima University, Higashihiroshima 739-8527, Japan
20 shared publications Ichiro Nishizaki
Hiroshima University Higashihiroshima Hiroshima Japan
11 shared publications- Hideki Katagiri
Hiroshima University
2 shared publications Hiroaki Takeuchi
Graduate School of Engineering, Hiroshima University
2 shared publications- Shin Wakitani
Hiroshima University
2 shared publications
Latest Publications
- Open Access
- 17 September 2026
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 8 (9) , 288
Behavioral Analysis of Transfer Learning in DQN-Based Pedestrian Agents Using Single-Agent Pretraining
Reinforcement-learning-based pedestrian agents can acquire adaptive behaviors without hand-crafted motion rules, but training from scratch in each environment is computationally expensive and often environment dependent. This paper investigates a two-stage transfer-learning framework for Deep Q-Network (DQN)-based pedestrian agents and analyzes how single-agent pretraining changes subsequent learning and behavior formation in multi-agent environments. A shared Q-network is first pretrained over four single-agent source tasks using Conservative Q-Learning with adaptive source-task allocation and is then transferred as the initial network of every agent in four multi-agent target tasks. Unlike fixed curriculum training, the source tasks are not traversed in a predetermined order; instead, experience collection is reallocated according to current collision and goal-progress performance. Compared with random initialization, the transferred network improves early-stage learning in intersection, bi-flow, and bi-door environments and significantly reduces target-task training time in these three tasks. In the bottleneck environment, the improvement is limited and the reduction in target-task training time is not statistically significant. Behavioral analysis further shows that pretraining changes early exploration: in the bi-door task, transferred agents reach goal-side and door regions earlier while spending less time near walls. Post-training trajectories also reveal collision avoidance and diverse route choices. These results clarify both the benefits and limitations of single-agent pretraining for efficient and interpretable behavior acquisition in multi-agent pedestrian simulation.
- 17 September 2026
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 8 (9) , 288
Open AccessBehavioral Analysis of Transfer Learning in DQN-Based Pedestrian Agents Using Single-Agent Pretraining
Reinforcement-learning-based pedestrian agents can acquire adaptive behaviors without hand-crafted motion rules, but training from scratch in each environment is computationally expensive and often environment dependent. This paper investigates a two-stage transfer-learning framework for Deep Q-Network (DQN)-based pedestrian agents and analyzes how single-agent pretraining changes subsequent learning and behavior formation in multi-agent environments. A shared Q-network is first pretrained over four single-agent source tasks using Conservative Q-Learning with adaptive source-task allocation and is then transferred as the initial network of every agent in four multi-agent target tasks. Unlike fixed curriculum training, the source tasks are not traversed in a predetermined order; instead, experience collection is reallocated according to current collision and goal-progress performance. Compared with random initialization, the transferred network improves early-stage learning in intersection, bi-flow, and bi-door environments and significantly reduces target-task training time in these three tasks. In the bottleneck environment, the improvement is limited and the reduction in target-task training time is not statistically significant. Behavioral analysis further shows that pretraining changes early exploration: in the bi-door task, transferred agents reach goal-side and door regions earlier while spending less time near walls. Post-training trajectories also reveal collision avoidance and diverse route choices. These results clarify both the benefits and limitations of single-agent pretraining for efficient and interpretable behavior acquisition in multi-agent pedestrian simulation.
- Open Access
Robust Flexibility Provision from DERs: A Network-Constrained Multi-Step Optimization Approach
This paper proposes a network-constrained multi-step optimization approach for robust flexibility provision from distributed energy resources (DERs) under photovoltaic (PV) generation uncertainty. The proposed method optimally schedules day-ahead battery operations based on PV output predictions and confidence intervals, while strictly satisfying network constraints. To ensure operational feasibility, the AC power flow is modeled using DistFlow equations. To bridge the gap between computational tractability and exact AC feasibility, a multi-step solution strategy is introduced. First, a linearized DistFlow (LinDistFlow) model is employed within a column-and-constraint generation algorithm to efficiently identify the worst-case scenario. Subsequently, the robust day-ahead battery schedule is determined by solving a second-order cone (SOC)-relaxed DistFlow model under the identified scenario. Finally, a post-processing exact recovery step is executed by solving the original non-convex DistFlow equations under the fixed battery schedule and the worst-case scenario. This crucial step compensates for approximation errors introduced by the LinDistFlow and SOC models, significantly enhancing practical operational AC feasibility under the identified critical condition. Extensive case studies on the IEEE 33-bus test system verify the effectiveness of the proposed multi-step approach in balancing computational efficiency and robust flexibility provision.
Open AccessRobust Flexibility Provision from DERs: A Network-Constrained Multi-Step Optimization Approach
This paper proposes a network-constrained multi-step optimization approach for robust flexibility provision from distributed energy resources (DERs) under photovoltaic (PV) generation uncertainty. The proposed method optimally schedules day-ahead battery operations based on PV output predictions and confidence intervals, while strictly satisfying network constraints. To ensure operational feasibility, the AC power flow is modeled using DistFlow equations. To bridge the gap between computational tractability and exact AC feasibility, a multi-step solution strategy is introduced. First, a linearized DistFlow (LinDistFlow) model is employed within a column-and-constraint generation algorithm to efficiently identify the worst-case scenario. Subsequently, the robust day-ahead battery schedule is determined by solving a second-order cone (SOC)-relaxed DistFlow model under the identified scenario. Finally, a post-processing exact recovery step is executed by solving the original non-convex DistFlow equations under the fixed battery schedule and the worst-case scenario. This crucial step compensates for approximation errors introduced by the LinDistFlow and SOC models, significantly enhancing practical operational AC feasibility under the identified critical condition. Extensive case studies on the IEEE 33-bus test system verify the effectiveness of the proposed multi-step approach in balancing computational efficiency and robust flexibility provision.
- Open Access
- 16 March 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (6) , 1000
Genetic Programming with Adaptive Population Restructuring for Dynamic Flexible Job Shop Scheduling
In the dynamic flexible job shop scheduling problem (DFJSP) where the environment changes irregularly, priority rules are used to calculate priorities for each job and machine, determining the processing order. To achieve efficient scheduling, it is necessary to select appropriate priority rules that match the problem’s characteristics whenever the environment changes. To address such problems, Genetic Programming (GP) has been proposed to derive mathematically expressed priority rules. Various GP-based methods exist, among which Population-based Fluctuation GP (PF-GP) is an efficient technique that reuses individuals adapted to problem characteristics. However, optimizing the DFJSP using PF-GP requires significant computational cost. Therefore, methods have been developed to adaptively change the population size for more efficient resource utilization. This paper modifies the adaptive population size change into a population growth method designed to balance scheduling performance and computational efficiency in the DFJSP. By applying this proposed method to various scheduling problems, this paper investigates its effectiveness. Furthermore, this paper compares population growth methods and demonstrates that the proposed method addresses conventional issues in existing population adjustment techniques, enabling the more efficient utilization of computational resources.
- 16 March 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (6) , 1000
Open AccessGenetic Programming with Adaptive Population Restructuring for Dynamic Flexible Job Shop Scheduling
In the dynamic flexible job shop scheduling problem (DFJSP) where the environment changes irregularly, priority rules are used to calculate priorities for each job and machine, determining the processing order. To achieve efficient scheduling, it is necessary to select appropriate priority rules that match the problem’s characteristics whenever the environment changes. To address such problems, Genetic Programming (GP) has been proposed to derive mathematically expressed priority rules. Various GP-based methods exist, among which Population-based Fluctuation GP (PF-GP) is an efficient technique that reuses individuals adapted to problem characteristics. However, optimizing the DFJSP using PF-GP requires significant computational cost. Therefore, methods have been developed to adaptively change the population size for more efficient resource utilization. This paper modifies the adaptive population size change into a population growth method designed to balance scheduling performance and computational efficiency in the DFJSP. By applying this proposed method to various scheduling problems, this paper investigates its effectiveness. Furthermore, this paper compares population growth methods and demonstrates that the proposed method addresses conventional issues in existing population adjustment techniques, enabling the more efficient utilization of computational resources.
- Open Access
- 17 December 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (24) , 4017
Two-Stage Analysis for Supply Chain Disruptions Considering the Trade-Off Between Profit Maximization and Adaptability
Considering the trade-off between profit maximization and adaptability to supply chain disruptions, we examine herein the decision-making for configuration and distribution plans in a supply chain. Supply chain disruptions are caused by facility accidents and disasters. In this work, we investigate an optimal configuration and distribution plan in the supply chain with disruptions, including the opening of additional facilities while maintaining the optimum supply amounts to customers in the profit maximization plan when no such disruptions occur. Assuming the existence of uncertainties in demands and supplies, we formulate a two-stage model with a simple recourse, in which decisions on the supply chain configuration are made at the first stage. Decisions on the distribution are made at the second stage after the demands and supplies are realized. For such a configuration and distribution in the supply chain, we propose TSA-SCD (Two-Stage Analysis for Supply Chain Disruptions), a novel decision-making framework considering the trade-off between profit maximization and adaptability to supply chain disruptions. Accordingly, we perform numerical experiments with different degrees of disruptions to verify the effectiveness of the proposed decision method.
- 17 December 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (24) , 4017
Open AccessTwo-Stage Analysis for Supply Chain Disruptions Considering the Trade-Off Between Profit Maximization and Adaptability
Considering the trade-off between profit maximization and adaptability to supply chain disruptions, we examine herein the decision-making for configuration and distribution plans in a supply chain. Supply chain disruptions are caused by facility accidents and disasters. In this work, we investigate an optimal configuration and distribution plan in the supply chain with disruptions, including the opening of additional facilities while maintaining the optimum supply amounts to customers in the profit maximization plan when no such disruptions occur. Assuming the existence of uncertainties in demands and supplies, we formulate a two-stage model with a simple recourse, in which decisions on the supply chain configuration are made at the first stage. Decisions on the distribution are made at the second stage after the demands and supplies are realized. For such a configuration and distribution in the supply chain, we propose TSA-SCD (Two-Stage Analysis for Supply Chain Disruptions), a novel decision-making framework considering the trade-off between profit maximization and adaptability to supply chain disruptions. Accordingly, we perform numerical experiments with different degrees of disruptions to verify the effectiveness of the proposed decision method.
- Open Access
- 7 November 2025
- Published by MDPI AG in AppliedMath
- Vol. 5 (4) , 159
ELPSO-C: A Clustering-Based Strategy for Dimension-Wise Diversity Control in Enhanced Leader Particle Swarm Optimization
In high-dimensional optimization, particle swarm optimization (PSO) algorithms often suffer from premature convergence due to stagnation in certain dimensions. This study proposes an enhanced variant, ELPSO-C, which integrates dimension-wise convergence detection with adaptive exploration mechanisms. By applying agglomerative clustering to inter-particle velocity diversity, ELPSO-C identifies dimensions showing signs of stagnation and selectively reintroduces diversity through targeted mutation strategies. The algorithm preserves global search capability while reducing unnecessary perturbation in well-explored dimensions. Experimental results on a suite of 18 benchmark functions across various dimensions demonstrate that ELPSO-C consistently achieves superior performance compared to existing PSO variants, especially in high-dimensional and complex landscapes. These findings suggest that dimension-aware adaptation is an effective strategy for improving PSO’s robustness and convergence quality.
- 7 November 2025
- Published by MDPI AG in AppliedMath
- Vol. 5 (4) , 159
Open AccessELPSO-C: A Clustering-Based Strategy for Dimension-Wise Diversity Control in Enhanced Leader Particle Swarm Optimization
In high-dimensional optimization, particle swarm optimization (PSO) algorithms often suffer from premature convergence due to stagnation in certain dimensions. This study proposes an enhanced variant, ELPSO-C, which integrates dimension-wise convergence detection with adaptive exploration mechanisms. By applying agglomerative clustering to inter-particle velocity diversity, ELPSO-C identifies dimensions showing signs of stagnation and selectively reintroduces diversity through targeted mutation strategies. The algorithm preserves global search capability while reducing unnecessary perturbation in well-explored dimensions. Experimental results on a suite of 18 benchmark functions across various dimensions demonstrate that ELPSO-C consistently achieves superior performance compared to existing PSO variants, especially in high-dimensional and complex landscapes. These findings suggest that dimension-aware adaptation is an effective strategy for improving PSO’s robustness and convergence quality.
- Open Access
- 9 July 2025
- Published by MDPI AG in AppliedMath
- Vol. 5 (3) , 88
ACS2-Powered Pedestrian Flow Simulation for Crowd Dynamics
Pedestrian flow simulations play a pivotal role in urban planning, transportation engineering, and disaster response by enabling the detailed analysis of crowd dynamics and walking behavior. While physical models such as the Social Force model and Boids have been widely used, they often struggle to replicate complex inter-agent interactions. On the other hand, reinforcement learning (RL) methods, although adaptive, suffer from limited interpretability due to their opaque policy structures. To address these limitations, this study proposes a pedestrian simulation framework based on the Anticipatory Classifier System 2 (ACS2), a rule-based evolutionary learning model capable of extracting explicit behavior rules through trial-and-error learning. The proposed model captures the interactions between agents and environmental features while preserving the interpretability of the acquired strategies. Simulation experiments demonstrate that the ACS2-based agents reproduce realistic pedestrian dynamics and achieve comparable adaptability to conventional reinforcement learning approaches such as tabular Q-learning. Moreover, the extracted behavior rules enable systematic analysis of movement patterns, including the effects of obstacles and crowd composition on flow efficiency and group alignment. The results suggest that the ACS2 provides a promising approach to constructing interpretable multi-agent simulations for real-world pedestrian environments.
- 9 July 2025
- Published by MDPI AG in AppliedMath
- Vol. 5 (3) , 88
Open AccessACS2-Powered Pedestrian Flow Simulation for Crowd Dynamics
Pedestrian flow simulations play a pivotal role in urban planning, transportation engineering, and disaster response by enabling the detailed analysis of crowd dynamics and walking behavior. While physical models such as the Social Force model and Boids have been widely used, they often struggle to replicate complex inter-agent interactions. On the other hand, reinforcement learning (RL) methods, although adaptive, suffer from limited interpretability due to their opaque policy structures. To address these limitations, this study proposes a pedestrian simulation framework based on the Anticipatory Classifier System 2 (ACS2), a rule-based evolutionary learning model capable of extracting explicit behavior rules through trial-and-error learning. The proposed model captures the interactions between agents and environmental features while preserving the interpretability of the acquired strategies. Simulation experiments demonstrate that the ACS2-based agents reproduce realistic pedestrian dynamics and achieve comparable adaptability to conventional reinforcement learning approaches such as tabular Q-learning. Moreover, the extracted behavior rules enable systematic analysis of movement patterns, including the effects of obstacles and crowd composition on flow efficiency and group alignment. The results suggest that the ACS2 provides a promising approach to constructing interpretable multi-agent simulations for real-world pedestrian environments.
- 13 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
WIP: Machine Learning Models for Predicting Student Performance in IoT-Enhanced Education
This work in progress resaerch-to-practice mainly contributes the development of a multistage classification method to distinguish between learners who are easily predictable and those who exhibit more complex patterns. This methodological innovation not only supports the efficient allocation of educational resources but also aids in customizing learning materials for learning management systems, enhancing the relevance and effectiveness of educational content. In Japan, the GIGA School Concept, which involves the use of one internet-connected electronic device per student, has been introduced in all elementary and junior high schools since 2020. The integration of IoT (Internet of Things) technology supported by such initiatives represents a significant shift towards creating more interactive and tailored learning environments. This evolution aims not only to enhance educational outcomes by providing individual electronic devices to learners but also to optimize learning results and operational efficiency. These technological tools enable learners to progress through their educational journey at their own pace, promoting a more learner-centered approach known as “Personalized Learning.” Simultaneously, educators can more effectively monitor and manage the learning process, enabling a more responsive and adaptive educational experience. At the central of this transformation is the role of machine learning models (such as neural networks and random forests) used to predict learners' performance based on past academic achievements. This predictive capability allows for the grouping of learners based on the predictability of their performance, further refining educational strategies to meet diverse learning needs. Furthermore, this study explores the practical application of these models through numerical experiments using actual learner data. The results highlight the potential of combining IoT technology and machine learning to revolutionize the educational domain by providing personalized learning experiences. Such an approach promises not only to improve learning outcomes by aligning educational content and strategies with individual learners' profiles but also to streamline the educational process, reduce the burden on educators, and optimize the overall educational environment. In conclusion, the integration of IoT and machine learning into education presents a visionary method for addressing the unique needs and potential of individual learners.
- 13 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
WIP: Machine Learning Models for Predicting Student Performance in IoT-Enhanced Education
This work in progress resaerch-to-practice mainly contributes the development of a multistage classification method to distinguish between learners who are easily predictable and those who exhibit more complex patterns. This methodological innovation not only supports the efficient allocation of educational resources but also aids in customizing learning materials for learning management systems, enhancing the relevance and effectiveness of educational content. In Japan, the GIGA School Concept, which involves the use of one internet-connected electronic device per student, has been introduced in all elementary and junior high schools since 2020. The integration of IoT (Internet of Things) technology supported by such initiatives represents a significant shift towards creating more interactive and tailored learning environments. This evolution aims not only to enhance educational outcomes by providing individual electronic devices to learners but also to optimize learning results and operational efficiency. These technological tools enable learners to progress through their educational journey at their own pace, promoting a more learner-centered approach known as “Personalized Learning.” Simultaneously, educators can more effectively monitor and manage the learning process, enabling a more responsive and adaptive educational experience. At the central of this transformation is the role of machine learning models (such as neural networks and random forests) used to predict learners' performance based on past academic achievements. This predictive capability allows for the grouping of learners based on the predictability of their performance, further refining educational strategies to meet diverse learning needs. Furthermore, this study explores the practical application of these models through numerical experiments using actual learner data. The results highlight the potential of combining IoT technology and machine learning to revolutionize the educational domain by providing personalized learning experiences. Such an approach promises not only to improve learning outcomes by aligning educational content and strategies with individual learners' profiles but also to streamline the educational process, reduce the burden on educators, and optimize the overall educational environment. In conclusion, the integration of IoT and machine learning into education presents a visionary method for addressing the unique needs and potential of individual learners.
- Open Access
- 30 October 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (21) , 4492
Data Envelopment Analysis Approaches for Multiperiod Two-Level Production and Distribution Planning Problems
This paper deals with two-level production and distribution planning problems in supply chain management where the leader is a distributor and the follower is a manufacturer. Assuming that the distributor can observe the input–output data in the production process, we formulated the data envelopment analysis (DEA) production problem corresponding to the production planning problem of the manufacturer. This paper proposes a novel data envelopment analysis (DEA) approach to solve a challenging multiperiod two-level production and distribution planning problem in supply chain management. The innovative idea behind the proposed approach is to allow the distributor to observe the input–output data regarding the production activities of the manufacturer, even if the distributor cannot fully comprehend all parameters of the manufacturer’s production cost minimization problem. This approach addresses the challenge of uncertain demands by employing a two-stage model with simple recourse and considering the usage of the input–output data. The paper demonstrates the validity of the proposed DEA approaches through computational experiments and discusses the accuracy, reliability, and importance of the input–output data. The proposed approach provides a practical and effective solution to the multiperiod two-level production and distribution planning problem in supply chain management, and can help decision-makers improve the efficiency and effectiveness of their operations. The innovative idea of allowing the distributor to observe the input–output data about the production activities of the manufacturer is a significant contribution to the field of supply chain management and has the potential to advance the state of the art in this area.
- 30 October 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (21) , 4492
Open AccessData Envelopment Analysis Approaches for Multiperiod Two-Level Production and Distribution Planning Problems
This paper deals with two-level production and distribution planning problems in supply chain management where the leader is a distributor and the follower is a manufacturer. Assuming that the distributor can observe the input–output data in the production process, we formulated the data envelopment analysis (DEA) production problem corresponding to the production planning problem of the manufacturer. This paper proposes a novel data envelopment analysis (DEA) approach to solve a challenging multiperiod two-level production and distribution planning problem in supply chain management. The innovative idea behind the proposed approach is to allow the distributor to observe the input–output data regarding the production activities of the manufacturer, even if the distributor cannot fully comprehend all parameters of the manufacturer’s production cost minimization problem. This approach addresses the challenge of uncertain demands by employing a two-stage model with simple recourse and considering the usage of the input–output data. The paper demonstrates the validity of the proposed DEA approaches through computational experiments and discusses the accuracy, reliability, and importance of the input–output data. The proposed approach provides a practical and effective solution to the multiperiod two-level production and distribution planning problem in supply chain management, and can help decision-makers improve the efficiency and effectiveness of their operations. The innovative idea of allowing the distributor to observe the input–output data about the production activities of the manufacturer is a significant contribution to the field of supply chain management and has the potential to advance the state of the art in this area.
- Open Access
- 11 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 90-97
DEA Approaches for Multiperiod Two-Level Production and Distribution Planning Problems
This paper extends the idea presented in Nishizaki et al. (2022) to address a multi-period two-level production and distribution planning problem in supply chain management. The leader is a distributor and the follower is a manufacturer, with input-output data observed over multiple periods. A Data Envelopment Analysis (DEA) production problem is formulated to correspond to the manufacturer's production planning problem. Due to the multi-period nature of the problem, uncertain demands are anticipated and a two-stage model with simple recourse is employed to manage discrepancies between supply and demand. The validity of the proposed DEA approaches is demonstrated through computational experiments.
- 11 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 90-97
Open AccessDEA Approaches for Multiperiod Two-Level Production and Distribution Planning Problems
This paper extends the idea presented in Nishizaki et al. (2022) to address a multi-period two-level production and distribution planning problem in supply chain management. The leader is a distributor and the follower is a manufacturer, with input-output data observed over multiple periods. A Data Envelopment Analysis (DEA) production problem is formulated to correspond to the manufacturer's production planning problem. Due to the multi-period nature of the problem, uncertain demands are anticipated and a two-stage model with simple recourse is employed to manage discrepancies between supply and demand. The validity of the proposed DEA approaches is demonstrated through computational experiments.
- Open Access
- 15 July 2023
- Published by The Institute of Systems, Control and Information Engineers in Transactions of the Institute of Systems, Control and Information Engineers
- Vol. 36 (7) , 187-198
Cooperative Electric Power Supply System in Distribution Networks for Power Supply in Disasters
This paper proposes a cooperative electric power supply system based on cooperative game theory, aiming to design monetary incentives for consumers to install energy resources that contribute to the continuous power supply to them in case of power interruption by disasters. The proposed system designs the incentives by maximizing the long-term profits gained by controlling photovoltaic generation systems (PVs), controllable loads, and batteries during normal operations. The proposed system employs a two-stage optimization method for scheduling battery operations under the uncertainty of PV generation during normal operations to alleviate its heavy computational burden. Since the profit allocated to each consumer participating in the proposed system is determined based on the imputation in the core, the solution of cooperative game theory, the consumers have no incentive to leave the grand coalition. When the power supply from the distribution network is interrupted during the disaster, the consumers cooperate to control their PVs and batteries to continue supplying the electric power to them using the installed resources until the power supply is restored. The effectiveness of the proposed system is verified by computational experiments under normal and disaster conditions.
- 15 July 2023
- Published by The Institute of Systems, Control and Information Engineers in Transactions of the Institute of Systems, Control and Information Engineers
- Vol. 36 (7) , 187-198
Open AccessCooperative Electric Power Supply System in Distribution Networks for Power Supply in Disasters
This paper proposes a cooperative electric power supply system based on cooperative game theory, aiming to design monetary incentives for consumers to install energy resources that contribute to the continuous power supply to them in case of power interruption by disasters. The proposed system designs the incentives by maximizing the long-term profits gained by controlling photovoltaic generation systems (PVs), controllable loads, and batteries during normal operations. The proposed system employs a two-stage optimization method for scheduling battery operations under the uncertainty of PV generation during normal operations to alleviate its heavy computational burden. Since the profit allocated to each consumer participating in the proposed system is determined based on the imputation in the core, the solution of cooperative game theory, the consumers have no incentive to leave the grand coalition. When the power supply from the distribution network is interrupted during the disaster, the consumers cooperate to control their PVs and batteries to continue supplying the electric power to them using the installed resources until the power supply is restored. The effectiveness of the proposed system is verified by computational experiments under normal and disaster conditions.