Round-Trip Time Estimation Using Hybrid Neuro-Fuzzy Based On Subtractive Clustering

Hassan Rizky Putra Sailellah; Suma Danu Ristianto

doi:10.54209/jatilima.v7i06.2159

Hassan Rizky Putra Sailellah Telkom University
Suma Danu Ristianto Telkom University

DOI: https://doi.org/10.54209/jatilima.v7i06.2159

Keywords: Round-Trip Time, Quality of Service, Adaptive Neuro-Fuzzy Inference System, Estimation, Subtractive Clustering

Article Metrics

Abstract view : 166 times

Abstract

Round-trip time (RTT) is a key latency indicator for quality-of-service (QoS) control and task orchestration in cloud–edge systems. However, RTT is highly time-varying due to congestion dynamics, routing changes, and fluctuating traffic conditions, motivating short-term prediction to enable proactive decision making. This paper investigates a hybrid neuro-fuzzy baseline for RTT prediction implemented using an Adaptive Neuro-Fuzzy Inference System (ANFIS) with subtractive-clustering-based initialization to avoid rule explosion in high-dimensional inputs. A controlled dataset was generated in Mininet using a dumbbell topology with injected delays (1–1000 ms). In total, 100,000 raw RTT records were collected (100 RTT measurements per run across 1000 runs) and aggregated into 1000 supervised samples paired with TCP-state features. Experiments followed a unified and reproducible protocol with a fixed 60/10/30 train/validation/test split, train-only feature standardization, train-only target normalization with inverse transformation for reporting, and validation-based checkpoint selection. The ANFIS baseline (radius ????=0.5r=0.5, 19 rules) achieved RMSE/ MAE/ MAPE/ ????2 of 1191.63/ 751.02/ 0.001921/ 0.999996 on validation and 1207.23/ 664.70/ 0.001311/ 0.999996 on testing. Training required 546.91 s, while inference remained lightweight (0.0846 s for 100 validation samples and 0.1493 s for 300 test samples). Diagnostic analyses using learning curves, parity plots, residual inspection, and empirical error distributions further supported the strong agreement between predicted and observed RTT values. These results indicate that ANFIS with subtractive clustering can deliver accurate and low-latency RTT prediction suitable for QoS-aware orchestration pipelines where training can be performed offline.

References

Aldhyani, T. H., Alrasheedi, M., Alqarni, A. A., Alzahrani, M. Y., & Bamhdi, A. M. (2020). Intelligent hybrid model to enhance time series models for predicting network traffic. IEEE Access, 8, 130431-130451.
AlQerm, I., & Pan, J. (2021). DeepEdge: A new QoE-based resource allocation framework using deep reinforcement learning for future heterogeneous edge-IoT applications. IEEE Transactions on Network and Service Management, 18(4), 3942-3954.
Putra, Y. A., Nuha, H. H., & Sailellah, H. R. P. (2024, November). Improving Online Computation Offloading in Mobile-Edge Computing Networks using Deep Reinforcement Learning. In 2024 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT) (pp. 847-852). IEEE.
Barbierato, L., Estebsari, A., Bottaccioli, L., Macii, E., & Patti, E. (2020). A distributed multimodel cosimulation platform to assess general purpose services in smart grids. IEEE Transactions on Industry Applications, 56(5), 5613-5624.
Chatterjee, T., Karmakar, R., Mitra, A., Ghosh, A., & Bhattacharya, S. (2021, July). ICon: How Can We Intelligently Predict TCP Congestion?. In 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT) (pp. 1-7). IEEE.
Chen, D., Cai, J., Huang, Y., & Lv, Y. (2021). Deep neural fuzzy system oriented toward high-dimensional data and interpretable artificial intelligence. Applied Sciences, 11(16), 7766.
Damaševičius, R., & Sidekerskienė, T. (2020). Short time prediction of cloud server round-trip time using a hybrid neuro-fuzzy network. Journal of artificial intelligence and systems., 2(1), 133-148.
Deng, L., & Tsang, D. H. (2025, June). Generative Matrix Completion for Real-Time Network Latency Estimation. In ICC 2025-IEEE International Conference on Communications (pp. 470-475). IEEE.
Fang, H., Yu, P., Wang, Y., Li, W., Zhou, F., & Ma, R. (2022, October). A novel network delay prediction model with mixed multi-layer perceptron architecture for edge computing. In 2022 18th International Conference on Network and Service Management (CNSM) (pp. 191-197). IEEE.
Giannakopoulos, P., van Knippenberg, B., Joshi, K. C., Calabretta, N., & Exarchakos, G. (2025). Morpheus: Lightweight RTT Prediction for Performance-Aware Load Balancing. arXiv preprint arXiv:2510.20506.
Ghosh, C. R., Ahsan, N., Islam, M., Noor, R., & MAshrafi, A. (2025). An SDN-based approach using RYU controller for load balancing and performance evaluation in hybrid networks with machine learning algorithms (Doctoral dissertation, Brac University).
Khababa, G., Bessou, S., Seghir, F., Harun, N. H., Almazyad, A. S., Jangir, P., & Mohamed, A. W. (2025). Collaborative filtering techniques for predicting web service qos values in static and dynamic environments: A systematic and thorough analysis. IEEE Access.
Kulkarni, R., Charudarahas, V., Tej, P. V., & Sharma, B. (2025, April). Machine Learning-Driven QoE Prediction for SDN Networks: A Hybrid Model Approach. In 2025 International Conference on Inventive Computation Technologies (ICICT) (pp. 1786-1791). IEEE.
Larrenie, P., Bercher, J. F., Lahsen-Cherif, I., & Venard, O. (2022, November). Low Complexity Adaptive ML Approaches for End-to-End Latency Prediction. In International Conference on Machine Learning for Networking (pp. 72-87). Cham: Springer Nature Switzerland.
Mousavi, A., Jalali, M., & Yaghoubi, M. (2021). Adaptive Neuro Fuzzy Networks based on Quantum Subtractive Clustering. arXiv preprint arXiv:2102.00820.
Oladipo, S., Sun, Y., & Adegoke, S. A. (2024, July). Hybrid neuro-fuzzy modeling for electricity consumption prediction in a middle-income household in Gauteng, South Africa: utilizing fuzzy C-means method. In International Conference on Neural Computing for Advanced Applications (pp. 59-73). Singapore: Springer Nature Singapore.
Oladipo, S., Sun, Y., & Amole, A. O. (2024). Investigating the influence of clustering techniques and parameters on a hybrid PSO-driven ANFIS model for electricity prediction. Discover Applied Sciences, 6(5), 265.
Pasco, C. D. R., Bernardini, F., & Antônio, A. D. A. (2023, June). In-network Latency Nowcast Using Data Stream Learning Models. In 2023 International Wireless Communications and Mobile Computing (IWCMC) (pp. 1214-1219). IEEE.
Sailellah, H., & Nuha, H. H. (2024, August). Round-trip time estimation using regularized extreme learning machine. In 2024 International Conference on Artificial Intelligence, Blockchain, Cloud Computing, and Data Analytics (ICoABCD) (pp. 79-84). IEEE.
Sailellah, H. R. P., Nuha, H. H., & Putrada, A. G. (2026). Round-Trip Time Estimation Using Enhanced Regularized Extreme Learning Machine. Network, 6(1), 10.
Sailellah, H. R. P., Santoso, G., & Setyorini (2025, October). Estimating Round-Trip Time Using Machine Learning Models: A Comparative Study of SVM, GAM, and Linear Regression. In 2025 IEEE 9th International Conference on Software Engineering & Computer Systems (ICSECS) (pp. 553-558). IEEE.
Sharma, G., Khare, R., Kulkarni, N., Pagare, S., & Tiwari, V. (2025). Design of an Iterative AI-Driven Latency Prediction and QoS-Aware Task Scheduling in Mobile Edge Computing: A Federated and Reinforcement Learning Process. In EPJ Web of Conferences (Vol. 328, p. 01071). EDP Sciences.
Thapliyal, S. (2024, March). Predicting Network Latency Using Adaptive Network Based Fuzzy Inference System. In 2024 3rd International Conference for Innovation in Technology (INOCON) (pp. 1-6). IEEE.
White, G., & Clarke, S. (2020). Short-term QoS forecasting at the edge for reliable service applications. IEEE Transactions on Services Computing, 15(2), 1089-1102.
Zhang, W., Feng, M., Krunz, M., & Volos, H. (2020, December). Latency prediction for delay-sensitive v2x applications in mobile cloud/edge computing systems. In GLOBECOM 2020-2020 IEEE Global Communications Conference (pp. 1-6). IEEE.
Zhang, W., Feng, M., & Krunz, M. (2023). Latency estimation and computational task offloading in vehicular mobile edge computing applications. IEEE Transactions on Vehicular Technology, 73(4), 5808-5823.