Preemptive SDN Load Balancing With Machine Learning for Delay Sensitive Applications
Bibliographic record
Abstract
SDN is a key-enabler to achieve scalability in 5G and Multi-access Edge Computing networks. To balance the load between distributed SDN controllers, the migration of the data plane components has been proposed. Different from most previous works which use reactive mechanisms, we propose to preemptively balance the load in the SDN control plane to support network flows that require low latency communications. First, we forecast the load of SDN controllers to prevent load imbalances and schedule data plane migrations in advance. Second, we optimize the migration operations to achieve better load balancing under delay constraints. Specifically, in the first step, we construct two prediction models based on Auto Regressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) approaches to forecast SDN controllers load. Then, we conduct a comparative study between these two models and calculate their accuracies and forecast errors. The results show that, in long-term predictions, the accuracy of LSTM model outperforms that of ARIMA by 55% in terms of prediction errors. In the second step, to select which data plane components to migrate and where the migration should happen under delay constraints, we formulate the problem as a non-linear binary program, prove its NP-completeness and propose a reinforcement learning algorithm to solve it. The simulations show that the proposed algorithm performs close to optimal and outperforms recent benchmark algorithms from the literature.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".