# siddeshkhandekar/edge-inference-orchestrator architecture

> Architecture diagram of the GitHub repository siddeshkhandekar/edge-inference-orchestrator, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-04). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/siddeshkhandekar/edge-inference-orchestrator
- Repository: https://github.com/siddeshkhandekar/edge-inference-orchestrator

## Overview

Edge Inference Orchestrator is a standard-library OS simulation for sensor-processing jobs, accompanied by a separate Cloud-IoT deployment blueprint. The main workflow runs CPU scheduling, concurrency demonstrations, deadlock-safety checks, and memory-address translations, then prints their results. Scheduling uses a fixed job dataset; the other simulations are independent modules. The README also describes future AI and cloud-data workflows, but presents them as future additions rather than implemented runtime components. The cloud blueprint is included as a documented product artifact; its contents were not sampled.

Main entry points: [`main.py`](https://github.com/siddeshkhandekar/edge-inference-orchestrator/blob/main/main.py) (Simulation runner), [`schedulers.py`](https://github.com/siddeshkhandekar/edge-inference-orchestrator/blob/main/schedulers.py) (CPU scheduling), [`jobs.py`](https://github.com/siddeshkhandekar/edge-inference-orchestrator/blob/main/jobs.py) (Sensor job data), [`synchronization.py`](https://github.com/siddeshkhandekar/edge-inference-orchestrator/blob/main/synchronization.py) (Race and mutex tests)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_orchestration["Engine orchestration"]
  node_runner["Simulation runner<br/>[main.py]"]
end

subgraph group_compute["Job scheduling"]
  node_jobs["Sensor job data<br/>[jobs.py]"]
  node_scheduling["CPU scheduling<br/>[schedulers.py]"]
end

subgraph group_concurrency["Concurrency"]
  node_sync["Race and mutex tests<br/>[synchronization.py]"]
end

subgraph group_resources["Resource simulation"]
  node_banker["Deadlock avoidance<br/>[bankers.py]"]
  node_memory["Address translation<br/>[memory_mgmt.py]"]
end

subgraph group_deployment["Cloud blueprint"]
  node_blueprint["Cloud-IoT blueprint"]
end

node_user(("Engine user"))

node_user -->|"runs"| node_runner
node_runner -->|"runs algorithms"| node_scheduling
node_runner -->|"loads dataset"| node_jobs
node_scheduling -->|"imports dataset"| node_jobs
node_runner -->|"runs tests"| node_sync
node_runner -->|"evaluates requests"| node_banker
node_runner -->|"translates addresses"| node_memory

click node_runner "https://github.com/siddeshkhandekar/edge-inference-orchestrator/blob/main/main.py"
click node_jobs "https://github.com/siddeshkhandekar/edge-inference-orchestrator/blob/main/jobs.py"
click node_scheduling "https://github.com/siddeshkhandekar/edge-inference-orchestrator/blob/main/schedulers.py"
click node_sync "https://github.com/siddeshkhandekar/edge-inference-orchestrator/blob/main/synchronization.py"
click node_banker "https://github.com/siddeshkhandekar/edge-inference-orchestrator/blob/main/bankers.py"
click node_memory "https://github.com/siddeshkhandekar/edge-inference-orchestrator/blob/main/memory_mgmt.py"
click node_blueprint "https://github.com/siddeshkhandekar/edge-inference-orchestrator/blob/main/docs/architecture_blueprint.md"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_runner,node_user toneBlue
class node_jobs,node_scheduling toneAmber
class node_sync toneMint
class node_banker,node_memory toneRose
class node_blueprint toneIndigo
```

## Components

### Engine orchestration

- [Simulation runner](https://github.com/siddeshkhandekar/edge-inference-orchestrator/blob/main/main.py): `main.py`

### Job scheduling

- [Sensor job data](https://github.com/siddeshkhandekar/edge-inference-orchestrator/blob/main/jobs.py): `jobs.py`
- [CPU scheduling](https://github.com/siddeshkhandekar/edge-inference-orchestrator/blob/main/schedulers.py): `schedulers.py`

### Concurrency

- [Race and mutex tests](https://github.com/siddeshkhandekar/edge-inference-orchestrator/blob/main/synchronization.py): `synchronization.py`

### Resource simulation

- [Deadlock avoidance](https://github.com/siddeshkhandekar/edge-inference-orchestrator/blob/main/bankers.py): `bankers.py`
- [Address translation](https://github.com/siddeshkhandekar/edge-inference-orchestrator/blob/main/memory_mgmt.py): `memory_mgmt.py`

### Cloud blueprint

- [Cloud-IoT blueprint](https://github.com/siddeshkhandekar/edge-inference-orchestrator/blob/main/docs/architecture_blueprint.md): `docs/architecture_blueprint.md`

### Other components

- **Engine user**

## Connections

- Engine user → Simulation runner: runs (evidence: `README.md`)
- Simulation runner → CPU scheduling: runs algorithms (evidence: `main.py`)
- Simulation runner → Sensor job data: loads dataset (evidence: `main.py`)
- CPU scheduling → Sensor job data: imports dataset (evidence: `schedulers.py`)
- Simulation runner → Race and mutex tests: runs tests (evidence: `main.py`)
- Simulation runner → Deadlock avoidance: evaluates requests (evidence: `main.py`)
- Simulation runner → Address translation: translates addresses (evidence: `main.py`)
