What question did this study set out to answer?

To optimize real-time service resource scheduling in smart tourism scenic spots under uncertain and dynamic spatiotemporal conditions using deep reinforcement learning.

August 16, 2026Advanced ElectromagneticsOpen Access

Optimizing Service Resource Allocation Strategies in Smart Tourism Scenic Spots Using Deep Reinforcement Learning

View Full Paper

Ask AI

Bookmark

Authors

HXH. Y. XiongWuhan Technical College of Communications HLH. LiuElectric Power Research Institute

Discussion

Member takes

Implication

Computational study demonstrates enhanced resource utilization and reduced waiting times in simulated tourism environments, suggesting scalable real-time spatiotemporal decision-making.

Key Points

To optimize real-time service resource scheduling in smart tourism scenic spots under uncertain and dynamic spatiotemporal conditions using deep reinforcement learning.
Formulated scenic resource scheduling as a partially observable Markov decision process (POMDP) and implemented an optimized Rainbow Deep Q-Network (Rainbow DQN).
Combined a hybrid CNN–LSTM feature extraction module with distributional reinforcement learning, dueling networks, and prioritized replay to process heterogeneous spatiotemporal data.
Conducted extensive simulation experiments across multiple visitor-flow and environmental scenarios to test a multi-objective reward function targeting wait times, resource use, and operational costs.
Achieved average visitor waiting times of 3.9 to 8.2 minutes under varying simulated flow conditions, outperforming standard reinforcement learning baselines.
Attained service resource utilization rates of 76.9% to 88.3% while maintaining robust scheduling performance under adverse conditions.

Cite This Study

Xiong et al. (2026) studied this question.

synapsesocial.com/papers/6a81796af2fb91fc834ac7d5 https://doi.org/10.7716/aem.v15i3.3159

View Full Paper

Ask AI

Bookmark

Implication

Computational study demonstrates enhanced resource utilization and reduced waiting times in simulated tourism environments, suggesting scalable real-time spatiotemporal decision-making.

Optimizing Service Resource Allocation Strategies in Smart Tourism Scenic Spots Using Deep Reinforcement Learning

Discussion

Member takes

Implication

Key Points

Cite This Study

Optimizing Service Resource Allocation Strategies in Smart Tourism Scenic Spots Using Deep Reinforcement Learning

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider