Real-Time Adaptive Resource Allocation in 5G Network Slicing Using Hybrid Optimization and AI-driven Traffic Prediction

Citation Author(s):
Samiullah
Samiullah
Submitted by:
Samiullah Samiullah
Last updated:
Fri, 01/03/2025 - 09:55
DOI:
10.21227/apqh-zc88
Data Format:
*.txt; *.m;
License:
Creative Commons Attribution
7 Views
Categories:
Artificial Intelligence
Wireless Networking
Machine Learning
Keywords:
5G Network Slicing, network slicing, Resource allocation, real-time adaptive algorithms, hybrid optimization, AI-driven traffic prediction, genetic algorithms, Particle swarm optimization, Differential Evolution, ARIMA, LSTM, Quality of Service, Energy Efficiency, Security
0
0 ratings - Please login to submit your rating.
ACCESS DATASET CITE SHARE/EMBED

Abstract 

In the evolving landscape of 5G network, network slicing has been considered as a key technology for the realization of multiple virtual networks running on a shared physical infrastructure, each designed to fulfill a specific service or application. However, with such networks, the dynamic and real-time allocation of these resources remains a prime concern, particularly with respect to highly variable conditions of traffic. In this paper, an adaptive novel real-time resource allocation algorithm under 5G network slicing is proposed, constructed by a hybrid optimization framework with AI-based traffic prediction. The proposed approach combines the genetic algorithm (GA), particle swarm optimization (PSO) algorithm, and differential evolution (DE) with a heuristic adaptive adjustment mechanism to make it possible for robust and high-efficiency solutions to the problem of resource allocation optimization. An AI-based traffic prediction model is proposed, which utilizes ARIMA and LSTM techniques to accurately predict traffic demand in the future in order to proactively allocate resources. Wide simulation results indicate that the proposed methodology brings significant performance improvement in terms of resource utilization, latency, throughput, QoS, energy efficiency, and security level. The proposed approach ensures a consistent level of resource use, low latency, stable throughput, a high level of QoS, and efficient energy and security. Such results indicate the potential of our approach in improving the adaptability and efficiency of the 5G network slicing. Future work is aimed at energy efficiency improvement, followed by the model being fine-tuned through real-world datasets and adapted to a large scale of complex network environments.

Instructions: 

# Real-Time Adaptive Resource Allocation in 5G Network Slicing

 

## Overview

This repository contains the MATLAB code used for the simulations in the paper titled "Real-Time Adaptive Resource Allocation in 5G Network Slicing Using Hybrid Optimization and AI-driven Traffic Prediction."

 

## Files

- `Samiu2.m`: Main script to run the simulations.

 

## Running the Simulations

1. **Prerequisites**:

    - Ensure MATLAB is installed on your system.

 

2. **Running the Script**:

    - Download or clone this repository.

    - Open MATLAB and navigate to the folder containing `Samiu2.m`.

    - Run the `Samiu2.m` script by typing `Samiu2` in the MATLAB command window.

 

## Description of Main Script

The `Samiu2.m` script performs the following tasks:

1. **Initialization**:

    - Defines the number of base stations, user equipment (UE), and slices.

    - Initializes traffic patterns and resource allocation.

 

2. **Simulation Parameters**:

    - Sets the simulation time and time step.

    - Initializes performance metrics arrays for resource utilization, latency, throughput, QoS, energy efficiency, and security level.

 

3. **Simulation Loop**:

    - For each time step:

        - Monitors current traffic.

        - Predicts future traffic using an AI-driven model.

        - Adjusts resource allocation heuristically.

        - Optimizes resource allocation using a hybrid optimization algorithm.

        - Evaluates performance metrics.

 

4. **Plot Results**:

    - Plots the results for resource utilization, latency, throughput, QoS, energy efficiency, and security level.

 

## Function Definitions

### `initializeTrafficPatterns(numUE, numSlices)`

- Initializes synthetic traffic patterns.

 

### `initializeResourceAllocation(numBaseStations, numSlices, sliceCapacity)`

- Initializes resource allocation for each slice across all base stations.

 

### `monitorTraffic(trafficPatterns, t, numBaseStations, numSlices)`

- Monitors current traffic at time `t`.

 

### `predictTrafficAI(currentTraffic)`

- Predicts future traffic using an AI-driven model (example implementation with ARIMA and LSTM).

 

### `heuristicAdjustment(resourceAllocation, currentTraffic, predictedTraffic)`

- Performs adaptive heuristic adjustment of resource allocation based on prediction accuracy.

 

### `optimizeResourceAllocationHybrid(resourceAllocation, currentTraffic, predictedTraffic)`

- Optimizes resource allocation using a hybrid optimization algorithm (GA, PSO, DE).

 

### `objectiveFunctionMultiObjective(x, predictedTrafficVector)`

- Defines the objective function for multi-objective optimization, combining resource allocation, energy efficiency, and security scores.

 

### `evaluateResourceUtilization(resourceAllocation)`

- Evaluates resource utilization.

 

### `evaluateLatency(resourceAllocation, currentTraffic)`

- Evaluates latency based on resource allocation and current traffic.

 

### `evaluateThroughput(resourceAllocation, currentTraffic)`

- Evaluates throughput based on resource allocation and current traffic.

 

### `evaluateQoS(resourceAllocation, currentTraffic)`

- Evaluates quality of service (QoS).

 

### `evaluateEnergyEfficiency(resourceAllocation)`

- Evaluates energy efficiency.

 

### `evaluateSecurityLevel(resourceAllocation)`

- Evaluates security level.

 

### `plotResults(resourceUtilization, latency, throughput, QoS, energyEfficiency, securityLevel)`

- Plots the performance metrics.

 

## Contact

For any questions or issues, please contact Samiullah at 19pwele5479@uetpeshawar.edu.pk.

 

Dataset Files

LOGIN TO ACCESS DATASET FILES

 

QUESTIONS?