A Dynamic Algorithm for Fog Computing Data Processing Decision Optimization
Bibliographic record
Abstract
Continuing Cloud service challenges like vendor lock-in and security in addition the Cloud clients' increased reliance on the service are motivating large Cloud tenants to build their own Clouds. Cloud providers still have the advantage (cost, availability and expertise) and therefore, a hybrid approach is still the first choice for Cloud clients aspiring to achieve partial independence. This promotes utilizing Fog computing architectures where resources rented from Cloud providers are supplemented by nodes on the edge of network that have limited computational capacity but are closer to request source. Fog nodes offer an opportunity to filter and process requests on the edge of the network in order to distribute the load and minimize the network congestion caused by low-value data. A question is, in turn, posed to Cloud architects on how to optimize the decision as to where to perform each step of the request service. The aim is to mitigate both the risk of pushing high loads to the Cloud servers which increases the cost; and the risk of localizing the whole process and losing the benefits from Cloud services. We build upon our previous work to solve this problem by proposing a novel dynamic programming algorithm to optimize the data processing decision for requests in a Fog environment. The dynamic programming algorithm achieves closer results to the optimal solution by reaching optimal increments of solutions from previous steps in feasible time. Initial experimental results comparing 5 heuristic algorithms are presented with the purpose of offering insight into contradicting factors impacting the problem (cost, network capacity, node and Cloud capacity).
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 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".