ENERGY CONSUMPTION PURE ALOHA(Μ-AMPS)

DataSet used in learning process of the traditional technique's operation, considering different devices and scenarios, perform the commutation through Pure ALOHA protocol, and make the device to operate with the best possible configuration.The control of energy consumption is essential for the operation of battery-operated systems, such as those used in IoT networks and sensors. The algorithms commonly employed for this purpose involve optimization functions with considerable complexity and rigorous control of the test environment. On the other hand, energy optimization algorithms implemented for the pure Aloha protocol, which serves as the basis for communication technologies in IoT networks such as LoraWAN, tend to be simpler and may result in packet collisions, leading to energy waste. In light of this, this proposal aims to implement an energy consumption reduction algorithm based on machine learning for the Aloha protocol. This algorithm will optimize multiple transmission variables, such as the number of bits per frame, transmission power, the number of hops from sender to receiver in the network, and data transmission rate. The expected outcome is to create a system that minimizes energy consumption during each transmission in the devices forming the network.

本数据集应用于传统操作技术的学习过程，涵盖多种设备和场景，通过纯ALOHA协议进行通信，并使设备以最佳配置运行。对于电池供电系统，如物联网网络和传感器所使用的系统，能耗控制对于其运行至关重要。通常，用于此目的的算法涉及复杂度较高的优化函数以及对测试环境的严格控制。另一方面，针对纯ALOHA协议所实现的能耗优化算法，该协议是物联网网络中如LoRaWAN等通信技术的基础，往往较为简单，可能导致数据包碰撞，进而造成能源浪费。鉴于此，本提议旨在实施一种基于机器学习的ALOHA协议能耗降低算法。该算法将优化多个传输变量，例如每帧的比特数、传输功率、发送者到接收者在网络中的跳数以及数据传输速率。预期成果是构建一个能够在网络中的设备传输过程中最小化能耗的系统。