# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: >-
  Adaptive Target-Condition Neural Network: DNN-Aided Load
  Balancing for Hybrid LiFi and WiFi Networks
message: ATCNN
type: dataset
authors:
  - given-names: Han
    family-names: Ji
    email: han.ji@ucdconnect.ie
    affiliation: University College Dublin
    orcid: 'https://orcid.org/0000-0003-2581-6316'
  - given-names: Qiang
    family-names: Wang
    email: qiang.wang@ucdconnect.ie
    affiliation: University College Dublin
  - given-names: Xiping
    family-names: Wu
    email: xiping.wu@ucd.ie
    affiliation: University College Dublin
  - given-names: Stephen J.
    family-names: Redmond
    email: stephen.redmond@ucd.ie
    affiliation: University College Dublin
  - given-names: Iman
    family-names: Tavakkolnia
    affiliation: University of Strathclyde
    email: i.tavakkolnia@strath.ac.uk
identifiers:
  - type: url
    value: 'https://arxiv.org/abs/2208.05035'
repository-code: 'https://github.com/HanJi-UCD/ATCNN'
abstract: >-
  Load balancing (LB) is a challenging issue in the hybrid
  light fidelity (LiFi) and wireless fidelity (WiFi)
  networks (HLWNets), due to the nature of heterogeneous
  access points (APs). Machine learning has the potential to
  provide a complexity-friendly LB solution with
  near-optimal network performance, at the cost of a
  training process. However, the state-of-the-art (SOTA)
  learning-aided LB methods need retraining when the network
  environment (especially the number of users) changes,
  significantly limiting its practicability. In this paper,
  a novel deep neural network (DNN) structure named adaptive
  target-condition neural network (A-TCNN) is proposed,
  which conducts AP selection for one target user upon the
  condition of other users. Also, an adaptive mechanism is
  developed to map a smaller number of users to a larger
  number by splitting their data rate requirements, without
  affecting the AP selection result for the target user.
  This enables the proposed method to handle different
  numbers of users without the need for retraining. The
  ablation study demonstrates the effectiveness and
  necessity of target-condition and adaptive mechanism in
  A-TCNN. In addition, testing results show that the trained
  A-TCNN can achieve 71\% and 66\% prediction accuracy with
  less than 10\% and 15\% throughput gap respectively,
  compared with baseline method for both 4 and 9 LiFi sizes.
  It is also proven that A-TCNN can obtain a network
  throughput comparable to two SOTA benchmarks while
  reducing the runtime by up to three orders of magnitude.
commit: Han Ji
version: '1.0'
date-released: '2023-07-07'