This paper presents a systematic approach for solving complex prediction problems with a focus on energy efficiency. The approach involves using neural networks, specifically recurrent and sequential networks, as the main tool for prediction. In order to test the methodology, a case study was conducted in the telecommunications industry to address the problem of energy efficiency in data centers. The case study involved comparing four recurrent and sequential neural networks, including recurrent neural networks (RNNs), long short-term memory (LSTM), gated recurrent units (GRUs), and online sequential extreme learning machine (OS-ELM), to determine the best network in terms of prediction accuracy and computational time. The results show that OS-ELM outperformed the other networks in both accuracy and computational efficiency. The simulation was applied to real traffic data and showed potential energy savings of up to 12.2% in a single day. This highlights the importance of energy efficiency and the potential for the methodology to be applied to other industries. The methodology can be further developed as technology and data continue to advance, making it a promising solution for a wide range of prediction problems.

As Internet Service Providers (ISPs) integrate the fifth generation (5G) technology standard for cellular broadband systems, they may face bursts of network traffic due to the future numerous connections. In this sense, our paper is focused on predicting traffic peaks via deep learning techniques, such as Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) of a real mobile core EPC node located in Chile. The results show that LSTM outperforms GRU in terms of traffic prediction by factor of 0.4 and in terms of computational cost, LSTM and GRU have identical behavior.

For years, it has been a great challenge for Internet Service Providers (ISP) to predict traffic load or future demand, since each bit of traffic is an economic cost to operators. Additionally, more and more users are adopting the different telecommunication services as well as the ISP must provide more bandwidth and reliability. In this sense, the study focuses on forecasting with neural network techniques, specifically Long Short-Term Memory (LSTM) and Online-Sequential Extreme Learning Machine (OS-ELM), the real traffic of a Chile ISP. The results show that OS-ELM outperforms LSTM in terms of computational cost by a factor of 2300, and in terms of network prediction, OS-ELM effectively competes with LSTM.

The exponential growth of encrypted network traffic and the increasing adoption of dynamic port allocation techniques have presented significant challenges to traditional traffic classification methods. In response, this paper introduces a novel flow-based online network traffic classification model leveraging machine learning techniques. The proposed approach extracts and processes 29 statistical, temporal, dynamics, and aggregation-based flow features, from 5-second time windows, enabling accurate real-time classification while preserving user privacy. The model is evaluated using network traffic data collected by the authors from various applications, including video streaming, gaming, video conferencing, web browsing, audio streaming, and web streaming. Additionally, the evaluation incorporates six publicly available benchmark datasets to validate the robustness and effectiveness of the proposed model. The obtained results demonstrate superior classification accuracy, consistently exceeding 96% and outperforming existing stateof-the-art approaches in the literature. The proposed method offers a robust and scalable solution for real-time traffic analysis, making it highly suitable for modern network environments and latency requirements.

This article presents a low cost solution based on visible light communication to report information from low rate sensors in indoor environments using the MIMO QAM channel and polar codes, encoding in Arduino Nano and decoding in a PYNO-Z1 FPGA.

The exponential increase in mobile data traffic in 5G networks requires advanced predictive tools for efficient resource management. In this paper, we present a comparative analysis of a predictive methodology based on Long Short Term Memory (LSTM), using input lags for traffic modeling within the mobile core network, using real Mobile Network Operator (MNO) data collected at 15-minute intervals over several days. The performance of the LSTM model is compared with a traditional Recurrent Neural Network (RNN). The results demonstrate that the LSTM achieves higher prediction accuracy and more stable computational performance across different configurations, with inference times ranging from 2.2 to 2.8 seconds.