Scholarlink

The paper discusses a traffic prediction as a multidimensional random process in a three-dimensional high-density Internet of Things network using a deep neural network architecture based on long short-term memory (LSTM). Themain purpose of the study is to increase the efficiency of time series forecasting due to taking into account the mutual dependence of individual flows produced by network nodes. Thepaper also proposes a method for adapting model parameters to changing network conditions.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Traffic Prediction as a Multidimensional Random Process in a Three-Dimensional High-density Internet of Things Network

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Alexander Paramonov,
  • Vasili Elagin,
  • Alexandera Grebenshchikova,
  • Anastasya Marochkina,
  • Artem Volkov

摘要

The paper discusses a traffic prediction as a multidimensional random process in a three-dimensional high-density Internet of Things network using a deep neural network architecture based on long short-term memory (LSTM). Themain purpose of the study is to increase the efficiency of time series forecasting due to taking into account the mutual dependence of individual flows produced by network nodes. Thepaper also proposes a method for adapting model parameters to changing network conditions.