Model-Driven Approach to Fading-Aware Wireless Network Planning Leveraging Multiobjective Optimization and Deep Learning
Apr 08, 2022
DOI: 10.1155/2022/4140522
Published in: Mathematical Problems in Engineering
Publisher: Hindawi
Efficient resource planning is recognized as one of the key enablers making the large-scale deployment of next-generation wireless networks available for mass usage. Modelling, planning, and software simulation tools reduce both the time needed and costs of their tuning and realization. In this paper, we propose a model-driven framework for proactive network planning relying on synergy of deep learning and multiobjective optimization. The predictions about service demand and energy consumption are taken into account. Also, the impact of degradations resulting from fading and cochannel interference (CCI) effects is also considered. The optimization task is treated as a component allocation problem (CAP) aiming to find the best possible base station allocation for the considered smart city locations with respect to performance and service demand constraints. The goal is to maximize Quality of Service (QoS) while keeping the costs and energy consumption as low as possible. The adoption of a model-driven approach in combination with model-to-model transformations and automated code generation does not only reduce the complexity, making experimentation more rapid and convenient at the same time, but also increase the overall reusability and expandability of the planning tool. According to the obtained results, the proposed solution seems to be promising not only due to achieved benefits but also regarding the execution time, which is shorter than that achieved in our previous works, especially for larger distances. Further, we adopt model-based representation of handover strategies within the planning tool, enabling examination of the dynamic behavior of user-created plan, which is not exploited in other similar works. The main contributions of the paper are (1) wireless network planning (WNP) metamodel, a modelling notation for network plans; (2) model-to-model transformation for conversion of WNP to generalized CAP metamodel; (3) prediction problem (PP) metamodel, high-level abstraction for representation of prediction-related regression and classification problems; (4) code generator that creates PyTorch neural network from PP representation; (5) service demand and energy consumption prediction modules performing regression; (6) multiobjective optimization model for base station allocation; (7) Handover Strategy (HS) metamodel used for description of dynamic aspects and adaptability relevant to network planning.
Other Researches
Model-Driven Approach for Generating Smart Contracts for Access Control
Access controls are principles and policies that are deployed on a system to ensure privileged access to system resources. Role-based access controls are a type of access controls which ensure access to resources based on users' roles. There has bee...
Modelling multi-party role-based access control policies for icontractml smart contracts
We propose a simple modelling language extending iContractML 2.0 for access control policies on smart contracts. The language supports multi-party authorisation and dynamic role-based access control (RBAC) where role members can be added or removed ...
Model-Driven Smart Contract Generation Leveraging ChatGPT
The trending large language model-based ChatGPT service, originally meant to be used as conversational agent, has been adopted in many areas - from programming to entertainment. On the other side, development of smart contracts for various blockchai...
Blockchain-Based Volunteers Management System
Blockchain technology is attracting huge attention across multiple industries. It sparks a revolution unlike anything else since the start of the Internet, since it goes against old ideas, changing the way that both individuals and organizations wil...
In recent years, blockchains have been exploited in areas way beyond finance, enabling numerous innovative usage scenarios and applications. However, the extension of the existing systems and applications in order to support data persistence on a bl...
On persisting EMF data using blockchains
In recent years, blockchain technology in synergy with smart contracts has opened new horizons within almost any field from entertainment to healthcare. However, in order to enable innovative usage scenarios, significant efforts are needed to adapt ...
Base station anomaly prediction leveraging model-driven framework for classification in Neo4j
Machine learning is one of key-enablers in case of novel usage scenarios and adaptive behavior within next generation mobile networks. In this paper, it is examined how model-driven approach can be adopted to automatize machine learning tasks aiming...
Vaccination is recognized as one of crucial measures in battle against COVID-19, contributing to both the reduction of its negative impact on infected person and overall spread reduction. In this paper, we focus on adoption of model-driven approach ...
Model-Driven Approach to Smart Grid Stability Prediction in Neo4j
Stability is of utmost importance when it comes to smart grid infrastructures. Dramatic parameter variations and fluctuations can lead to wrong decisions, which could lead to fatal consequences. In this paper, we propose a model-driven methodology f...
A Utility to Transform CSV Data into EMF
With the era of data evolution, enterprises increasingly depend on data utilization tools to import or export data from various data sources. Traditionally, enterprises archive such data into row formats, commonly in CSV files. The flat representati...
A Model-Driven Approach for Solving the Software Component Allocation Problem
The underlying infrastructure paradigms behind the novel usage scenarios and services are becoming increasingly complex—from everyday life in smart cities to industrial environments. Both the number of devices involved and their heterogeneity make t...
Model-driven multi-objective optimization approach to 6G network planning
Ultra high-speed and reliable next-generation 6G mobile networks are recognized as key enablers for many innovative scenarios in smart cities – from vehicular use cases and surveillance to healthcare. However, deployment of such network requires tre...
Test case prioritization for model transformations
The application of model transformations is a critical component in Model-Driven Engineering (MDE). To ensure the correctness of the generated models, these model transformations need to be extensively tested. However, during the regression testing ...
A Framework for the Regression Testing of Model-to-Model Transformations
Background: Model transformations play a key role in Model-Driven Engineering (MDE). Testing model transformation is an important activity to ensure the quality and correctness of the generated models. However, during the evolution and maintenance o...
Meta-Heuristics for Solving the Software Component Allocation Problem
The software component allocation problem is concerned with mapping a set of software components to the computational units available in a heterogeneous computing system while maximizing a certain objective function. This problem is important in the...
Extending UML Use Case Diagrams to Represent Non-Interactive Functional Requirements
Background: The comprehensive representation of functional requirements is a crucial activity in the analysis phase of the software development life cycle. Representation of a complete set of functional requirements helps in tracing business goals e...
On Utilizing Model Transformation for the Performance Analysis of Queueing Networks
In this paper, we present an approach for model transformation from Queueing Network Models (QNMs) into Queueing Petri Nets (QPNs). The performance of QPNs can be analyzed using a powerful simulation engine, SimQPN, designed to exploit the knowledge...
We extend an approach to component allocation on heterogeneous embedded systems using Coloured Petri Nets (CPNs). We improve the CPN model for the embedded systems and outline a technique that exploits CPN Tools, a well-known CPN tool, to efficientl...
ATL Transformation of Queueing Networks to Queueing Petri Nets
This paper presents an approach for model transformation from Queueing Network Models (QNMs) into Queueing Petri Nets (QPNs). This would open up the benefits of QPNs in analyzing the performance of QNMs. We present meta...
Model-to-Model based Approach for Software Component Allocation in Embedded Systems
Due to the popularity and heterogeneity of embedded systems, the problem of software component (SW-component) allocation in such systems is receiving increasing attention. Addressing this problem using a graphical modeling language s...
Server consolidation for heterogeneous computer clusters using Colored Petri Nets and CPN Tools
In this paper, we present a new approach to server consolidation in heterogeneous computer clusters using Colored Petri Nets (CPNs). Server consolidation aims to reduce energy costs and improve resource utilization by reducing the number of servers ...