Load Balancing and Resource Allocation in Smart Cities using Reinforcement Learning
Bibliographic record
Abstract
Today, smart city technology is being adopted by many municipal governments to improve their services and to adapt to growing and changing urban population. Implementing a smart city application can be one of the most challenging projects due to the complexity, requirements and constraints. Sensing devices and computing components can be numerous and heterogeneous. Increasingly, researchers working in the smart city arena are looking to leverage edge and cloud computing to support smart city development. This approach also brings a number of challenges. Two of the main challenges are resource allocation and load balancing of tasks associated with processing data from sensors, etc. This can be particularly challenging depending on the frequency that tasks come and go, their complexity, the level of resources, etc. This is a dynamically changing environment and static allocation strategies are not effective. This thesis investigates a reinforcement learning approach to dynamically allocate tasks to resources and try to ensure balanced loads on processing elements. The agent follows a Multi-Observation Single-State (MOSS) model which allows it to observe processed features from multiple sources at a single step. Those features represent multiple registered virtual machines (executors). The agent tries to orchestrate the arriving task to one of the executor candidates based on the task's characteristics and current condition of the executor. We introduce a model of a smart city computational infrastructure, describe our approach to reinforcement learning and present our algorithm for task allocation. We illustrate the agent behavior through simulations and show how its performance improves as it learns the environment.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 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".