LDMP-FEC: A Real-Time Low-Latency Scheduling Algorithm for Video Transmission in Heterogeneous Networks

Comments 1:

The evaluation relies entirely on simulations, which limits confidence in the algorithm’s real-world performance. Heterogeneous networks are inherently unpredictable, with mobility patterns, congestion, and interference varying widely. These factors, crucial in practical scenarios, are not adequately addressed or explored in the paper.

Response 1: 

Thank you for pointing this out. We acknowledge the importance of real-world validation and have addressed this as part of the future work section in the revised manuscript. Specifically, we highlight plans to conduct experiments in real-world dynamic scenarios, including drone-based video streaming and vehicular communications. While our current study is based on simulations, we have ensured that the simulation parameters (e.g., packet loss, delay, and jitter) are representative of real-world conditions. These simulations demonstrate the robustness of the LDMP-FEC algorithm in heterogeneous network environments.

Comments 2:

The complexity of LDMP-FEC raises concerns about its feasibility in resource-constrained environments, such as mobile devices or IoT systems. The paper lacks any discussion on the computational cost or scalability of the algorithm, which are critical factors for deployment in real-world applications.

Response 2:

Thank you for your comment. While we acknowledge that an in-depth analysis of computational cost was not included in the current study, the primary focus of this work is to validate the feasibility and effectiveness of the LDMP-FEC algorithm under various network conditions. Future work will explore the computational complexity and scalability in detail, particularly in resource-constrained environments such as IoT systems and mobile devices. This direction has been added to the roadmap for future research in the Conclusion section. This will include testing the algorithm on hardware with limited resources and conducting a detailed study on computational efficiency and scalability.

Comments 3:

Positioning LDMP-FEC in the context of adaptive scheduling solutions such as GADaM and Peekaboo would provide a clearer understanding of its unique contributions and practical relevance.

Response 3: 

Thank you for this suggestion. In the revised manuscript, we emphasize the unique contributions of LDMP-FEC, particularly its integration of FEC recovery mechanisms to address packet loss and reduce latency. While our study does not directly compare LDMP-FEC with GADaM and Peekaboo due to differing focuses, we acknowledge the relevance of these approaches and have cited the suggested works to provide better context for our contributions. Future research will explore a comparative analysis to highlight performance differences.

Comments 4:

Outlining a roadmap for future work could help maximize the impact of this promising research.

Response 4:

We have expanded the Conclusion section to include a detailed roadmap for future work. Key directions include:

1. Extending LDMP-FEC to highly dynamic environments, such as drone-based video streaming and vehicular communication scenarios.

2. Incorporating reinforcement learning techniques to enhance the adaptability of the algorithm.

3. Exploring hybrid approaches that combine FEC with real-time predictive scheduling to improve performance across diverse application scenarios.

5. Additional clarifications

We appreciate the valuable feedback and have made all necessary revisions to address the concerns raised. Please feel free to contact us for any further clarifications or additional details.

Thank you once again for your insightful comments.

Comments 1:

It is unclear what types of multiple routing paths you mean. Do you mean different paths within the same type of wireless networks or different paths through different types of networks (e.g., paths in 4/5G and WiFi)? If the latter one is what you are studying, you probably need to specify the types of heterogeneous networks as other types of wireless networks may bring different properties to data which can affect your methods.

Response 1:

Thank you for this insightful comment. We acknowledge the need for clarification regarding the types of multiple routing paths considered in our study. In the revised manuscript, we have specified that the LDMP-FEC algorithm was tested in a heterogeneous network environment comprising different types of networks, such as 4G/5G cellular networks and WiFi. These networks exhibit diverse characteristics, such as varying bandwidth, latency, and packet loss rates, which were explicitly considered in our simulation parameters. This clarification has been added to the Introduction and Methodology sections .

Comments 2:

Use scheduling to enhance multimedia communication performance is a classic topic in networking and communications. Many results have been proposed. The authors should conduct more comprehensive reviews to demonstrate the novelty/contribution. For example, real-time scheduling for multimedia services, efficient resource utilization for multi-flow wireless multicasting transmissions. Furthermore, the paper claims that it considers mobile multimedia communications. How can mobility affect the multimedia communications and your algorithms? Perhaps the authors can read these papers: seamless multimedia services over all-IP based infrastructures: the EVOLUTE approach, resource-efficient seamless transitions for high-performance multi-hop UAV multicasting, etc.

Response 2:

We appreciate this valuable suggestion. In the revised manuscript, we have expanded the Related Work section to include a more comprehensive review of scheduling techniques for multimedia communications. Additionally, we have discussed the potential impact of mobility on multimedia communications and the applicability of the LDMP-FEC algorithm under mobile scenarios. While our current work does not explicitly address mobility, we recognize its importance and have highlighted this as a key direction for future research in the Conclusion section. The suggested references have been reviewed and appropriately cited to provide additional context.

Comments 3:

The experiment section could be improved. The real-world platform is great but a bit limited, particularly in terms of multiple paths. Also, please justify how the evaluated performance metrics may demonstrate the achieved research study objectives.

Response 3:

Thank you for your constructive feedback. In the revised manuscript, we have elaborated on the experiment setup and provided additional justification for the selected performance metrics, including playable frame rate (PFR) and end-to-end latency. These metrics were chosen as they directly reflect the quality of multimedia transmission and the effectiveness of the LDMP-FEC algorithm in heterogeneous networks. While our current experiments focus on simulated environments, we have outlined plans to conduct real-world tests involving multiple paths and more dynamic scenarios as part of future work. These updates can be found in the Experimentation and Conclusion sections。

4. Additional clarifications

Thank you for your constructive feedback. In addition to addressing the specific comments, we have reviewed the entire manuscript to ensure clarity and coherence. The revised manuscript reflects these updates, and we remain available for any further clarifications or revisions that may be necessary.

Comments 1:

Could you include diagrams that illustrate the packet flow through different subflows in the network, emphasizing how the LDMP-FEC algorithm manages packet scheduling and redundancy.

Response 1:

Thank you for your suggestion. In the revised manuscript, we have added a diagram to illustrate the packet flow across different subflows in the network. This diagram highlights how the LDMP-FEC algorithm performs packet scheduling and redundancy management to ensure reliable transmission.

Comments 2:

Could you provide a numerical comparison of the LDMP-FEC algorithm with at least two existing algorithms (e.g., Round-Robin and another FEC method). Present results for metrics such as latency, packet loss, and PSNR in a well-organized table.

Response 2:

We appreciate your suggestion and have included a numerical comparison of the LDMP-FEC algorithm with Round-Robin scheduling and MinRTT, which serves as a baseline FEC method. The comparison results are presented in a new table, which includes key metrics such as latency, packet loss rate, and PSNR. This table demonstrates the advantages of LDMP-FEC in achieving lower latency and packet loss while maintaining high video quality. Specifically, LDMP-FEC shows significant improvements in end-to-end performance compared to MinRTT.

Comments 3:

Could you offer a more detailed explanation of the steps involved in the LDMP-FEC algorithm to help readers clearly understand the methodology.

Response 3:

Thank you for pointing this out. We have expanded the Methodology section to provide a more detailed explanation of the LDMP-FEC algorithm. Additionally, the new data flow results included in the manuscript already provide a clear demonstration of the algorithm's operational steps and effectiveness in real-time scheduling and redundancy recovery. These updates aim to improve the reader’s understanding of the algorithm’s design and implementation.

4. Response to Comments on the Quality of English Language

Point 1: Correct grammatical errors to improve the overall readability of the text.

Response 1:

We appreciate your feedback regarding language improvements. The manuscript has undergone a thorough review for grammar, spelling, and readability. Necessary corrections have been made to ensure clarity and coherence throughout the text.

5. Additional clarifications

Thank you once again for your valuable feedback. We believe the revisions made in response to your comments have significantly improved the quality of the manuscript. Please do not hesitate to reach out if further clarifications are required.