Heuristic-Based Computing-Aware Routing for Dynamic Networks

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This paper proposes a heuristic-based algorithm (H-CAR) for computing-aware routing in dynamic networks, modeling time-varying node and edge weights based on QoE metrics. The paper is well-structured, clearly defines the problem, and presents an innovative solution. Experimental results convincingly demonstrate the efficiency and accuracy of H-CAR.

A few areas could be strengthened. The paper mentions that the landmark table is "pre-calculated," but does not detail its computational cost or update frequency in dynamic environments. It also highlights the need for "sufficient and high-quality data" without discussing the challenges of obtaining and maintaining such data in real-world scenarios, which is critical for practical implementation.

Author Response

Please refer to the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The paper studies computing-power-aware routing algorithm. Algorithms are designed and some simulations are implemented. The reviewer has the following comments.

1. The introduction does not clearly describe the unique challenges of computing-power-aware routing. Many routing algorithms were designed, Dijkstra, A-start. It seems that computing power could just be an item to form a combined weight for these existing algorithms.
2. The paper also thinks that the proposed solution is a QoE based routing. The paper says – the QoE is evaluated by both the transmission process and computation process. However, both of them are not QoE-related metrics or processes. I suggest that the authors refer to the paper to understand QoE: data-driven QoS and QoE management in smart cities: a tutorial study
3. There are different math symbols and equations. However, they are not well presented or justified. For example, in π_{u,v,t }= {(u, v1), (u2, v2), . . . , is it u_1in the first item? (3) is also confusing. What are the purposes for (5)-(7)?
4. Simulations evaluate metrics like accuracy and time cost. How are they related to computing-power-related routing? How are they related to your research motivations?

Author Response

Please refer to the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

Comments and Suggestions for Authors

Thank you for addressing my comments. I have no further comments.