Leveraging Generative AI for Database Migration: A Comprehensive Approach for Heterogeneous Migrations
Bibliographic record
Abstract
In this paper, the author seeks to determine the extent to which generative AI particularly the Large Language Models can redefine Database Migration. The conventional techniques that are used for migrating data to next generation databases entail scripting as well as mapping manual work which are prone to errors, cumbersome and demand the services of an expert. This research aims at developing an integral solution based on LLMs that can assist at specific and critical phases of the migration process, especially for heterogeneous migration between distinct platforms of databases. The authors specifically point out how LLMs are used for analyzing the source database schema, for handling schema translation and data type mapping automatically and for interpreting and converting other database-dependent code like stored procedures and functions. The use of LLMs in the research also seeks to achieve a major reduction in manual work, enhancement of accuracy, and the general time taken in the migration processes. The paper also considers the position of LLMs within the performance enhancement, security. Experimentations on a modified version of a Gemini model on a sample Oracle to PostgreSQL database migration justify the proposed approach. The analysis points out significant gains in precision and performance besides noticeable reduction in the likelihood of errors from the use of traditional techniques. DOI : https://doi.org/10.52783/iej.9
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".