PDP-OmniSim

Features

• License Dual Licensing Model PDP-OmniSim is offered under a dual licensing model: Open Source License (GPL v3.0) Free for academic, research, and non-commercial use Required: Derivative works must be open source Ideal for: Universities, researchers, students Commercial License Required for commercial applications and proprietary derivatives Includes: Technical support, customization services Ideal for: Companies, startups, commercial products For commercial licensing inquiries, please contact: tlcagford@gmail.com 🏛️ Acknowledgments This project represents independent research and development efforts. Author: Tony E. Ford Contact: tlcagford@gmail.com Repository: https://github.com/tlcagford/PDP-OmniSim Documentation: Docs Folder Issues: GitHub Issues Advancing computational simulation through innovative research and development. About PDP-OmniSim is an advanced computational framework for simulating parallel and distributed processing systems, with cutting-edge applications in computational neuroscience, distributed computing, and complex systems modeling. The framework provides researchers with robust tools for large-scale simulations of networked systems Topics computer-science distributed-systems bioinformatics-pipeline quantum-computing data-analysis simulations pdp parrallel-computing Resources Readme Activity Stars 0 stars Watchers 0 watching Forks 0 forks Releases 1 v1.0.1 Latest 1 minute ago Packages No packages published Publish your first package Languages Python 99.8% Shell 0.2% Suggested workflows Based on your tech stack
• 🎯 Key Scientific Contributions 🔬 Interdisciplinary Research Domains Computational Neuroscience: Large-scale neural population dynamics, brain-inspired computing architectures, and neuro-symbolic AI systems Distributed Systems: Scalable parallel processing simulations, resource allocation optimization, and fault-tolerant computing Complex Systems: Emergent behavior in networked systems, self-organizing criticality, and adaptive network topologies Machine Learning: Distributed training paradigms, federated learning simulations, and neuromorphic computing models 🧩 Core Methodologies & Algorithms Discrete Event Simulation (DES): High-precision timing models with event-driven architecture Agent-Based Modeling (ABM): Multi-scale interactions with heterogeneous agent populations Monte Carlo Methods: Statistical sampling for uncertainty quantification and sensitivity analysis Graph Theory Applications: Advanced network topology analysis and dynamic graph algorithms Stochastic Processes: Markov chains, Poisson processes, and Brownian motion simulations 📊 Architecture & Design System Architecture PDP-OmniSim/ ├── Core/ │ ├── Simulation Engine (Event-driven core) │ ├── Scheduler (Priority-based event queue) │ └── Metrics Collector (Real-time analytics) ├── Models/ │ ├── Network Topologies (Graph-based models) │ ├── Processing Units (CPU/GPU abstractions) │ └── Communication Protocols (Message passing) ├── Analysis/ │ ├── Statistical Tools (Hypothesis testing) │ ├── Visualization (Multi-dimensional plots) │ └── Benchmarking (Performance metrics) └── Applications/ ├── Neuroscience (Neural mass models) ├── Distributed Computing (Load balancing) └── Complex Systems (Cascade failures) Mathematical Foundations 1. Queueing Theory Models M/M/1 Queues: Single-server exponential service times M/M/c Queues: Multi-server load distribution G/G/1 Queues: General arrival and service distributions Priority Queues: Preemptive and non-preemptive scheduling 2. Network Topology Models # Small-world networks (Watts-Strogatz) C = p * ln(N) / N # Clustering coefficient L ~ ln(N) / ln(K) # Characteristic path length # Scale-free networks (Barabási-Albert) P(k) ~ k^(-γ) # Power-law degree distribution 3. Neural Dynamics # Wilson-Cowan model for neural populations dE/dt = -E + S(c₁*E - c₂*I + P) dI/dt = -I + S(c₃*E - c₄*I + Q) 🚀 Installation & Setup System Requirements Python: 3.8, 3.9, 3.10, or 3.11 Memory: 8GB RAM minimum, 16GB+ recommended for large simulations Storage: 1GB free space, SSD recommended for I/O intensive workloads Processor: Multi-core CPU (8+ cores ideal), GPU optional for acceleration Installation Methods Basic Installation pip install pdp-omnisim Development Installation git clone https://github.com/tlcagford/PDP-OmniSim cd PDP-OmniSim # Create virtual environment python -m venv pdp_env source pdp_env/bin/activate # Windows: pdp_env\Scripts\activate # Install with development dependencies pip install -e ".[dev]" # Verify installation python -c "import pdp_omnisim; print('Installation successful!')" 💻 Usage Examples Basic Neural Population Simulation import pdp_omnisim as pdp import numpy as np import matplotlib.pyplot as plt # Create a neural mass model simulation sim_config = { "num_populations": 4, "connectivity": "small_world", "simulation_time": 10.0, # seconds "time_step": 0.001, # 1ms resolution "noise_level": 0.1 } simulator = pdp.NeuralMassSimulator(**sim_config) results = simulator.run() # Analyze results power_spectrum = pdp.analysis.spectral_analysis(results.timeseries) phase_synchronization = pdp.analysis.phase_sync(results.timeseries) # Visualize fig, axes = plt.subplots(2, 2, figsize=(12, 10)) pdp.visualization.plot_timeseries(results.timeseries, ax=axes[0,0]) pdp.visualization.plot_connectivity(simulator.connectivity_matrix, ax=axes[0,1]) pdp.visualization.plot_spectrum(power_spectrum, ax=axes[1,0]) pdp.visualization.plot_synchronization(phase_synchronization, ax=axes[1,1]) plt.tight_layout() plt.savefig('neural_simulation_results.png', dpi=300, bbox_inches='tight') Distributed Computing Performance Analysis from pdp_omnisim import DistributedSystemSimulator from pdp_omnisim.topology import DataCenterTopology # Simulate cloud computing environment dc_topology = DataCenterTopology( racks=10, servers_per_rack=20, network_bandwidth=10, # Gbps storage_latency=0.1 # ms ) simulator = DistributedSystemSimulator( topology=dc_topology, workload_type="scientific_computing", scheduling_algorithm="heterogeneous_earliest_finish_time", failure_model="weibull_distribution" ) # Run large-scale simulation metrics = simulator.simulate( duration=24 * 3600, # 24 hours warmup_period=3600, # 1 hour warmup random_seed=42 ) print(f"Overall System Efficiency: {metrics.efficiency:.3f}") print(f"Job Completion Rate: {metrics.completion_rate:.2%}") print(f"Resource Utilization: {metrics.utilization:.2%}") Advanced Complex Systems Research import pdp_omnisim.complex_systems as cs # Study information diffusion in social networks social_network = cs.SocialNetworkModel( num_agents=10000, network_type="scale_free", opinion_dynamics="bounded_confidence", influence_model="linear_threshold" ) # Simulate rumor spread initial_seeds = social_network.get_central_nodes(k=10) diffusion_process = social_network.simulate_diffusion( initial_active=initial_seeds, max_steps=100, threshold=0.3 ) # Analyze cascade properties cascade_metrics = cs.analyze_cascade(diffusion_process) critical_points = cs.find_critical_points(diffusion_process) print(f"Cascade Size: {cascade_metrics.size}") print(f"Cascade Duration: {cascade_metrics.duration}") print(f"Virality Coefficient: {cascade_metrics.virality:.3f}") 📈 Performance Benchmarks Scalability Analysis (Strong Scaling) Cores Simulation Time (s) Speedup Efficiency Memory (GB) 1 356.2 1.00x 100.0% 2.1 4 92.7 3.84x 96.0% 2.3 16 25.1 14.19x 88.7% 2.8 64 7.8 45.67x 71.4% 4.2 Accuracy Validation Metric Theoretical Simulated Error Queue Wait Time 12.5s 12.47s 0.24% Network Latency 45ms 44.8ms 0.44% Throughput 1250 ops/s 1246 ops/s 0.32% 🔬 Research Applications Neuroscience & Brain Simulation Large-scale neural mass models with realistic connectivity Spike-timing dependent plasticity (STDP) learning rules Whole-brain simulation using connectome data Neuromodulation effects on network dynamics Distributed Systems & Cloud Computing Data center performance optimization Edge computing resource allocation Federated learning system design Blockchain consensus mechanism analysis Complex Systems & Network Science Epidemiological modeling of disease spread Social network information diffusion Financial market contagion effects Critical infrastructure resilience 📚 Publications & Citations Recommended Citation Format @software{PDP_OmniSim_2024, title = {PDP-OmniSim: Parallel and Distributed Processing Simulation Framework}, author = {Ford, Tony E.}, year = {2024}, publisher = {GitHub}, journal = {GitHub repository}, howpublished = {\url{https://github.com/tlcagford/PDP-OmniSim}}, version = {1.0.0} }

Follow PDP-OmniSim

PDP-OmniSim Web Site