Presently, a green Internet of Things (IoT) based energy aware network plays a significant part in the sensing technology. The development of IoT has a major impact on several application areas such as healthcare, smart city, transportation, etc. The exponential rise in the sensor nodes might result in enhanced energy dissipation. So, the minimization of environmental impact in green media networks is a challenging issue for both researchers and business people. Energy efficiency and security remain crucial in the design of IoT applications. This paper presents a new green energy-efficient routing with DL based anomaly detection (GEER-DLAD) technique for IoT applications. The presented model enables IoT devices to utilize energy effectively in such a way as to increase the network span. The GEER-DLAD technique performs error lossy compression (ELC) technique to lessen the quantity of data communication over the network. In addition, the moth flame swarm optimization (MSO) algorithm is applied for the optimal selection of routes in the network. Besides, DLAD process takes place via the recurrent neural network-long short term memory (RNN-LSTM) model to detect anomalies in the IoT communication networks. A detailed experimental validation process is carried out and the results ensured the betterment of the GEER-DLAD model in terms of energy efficiency and detection performance.

中文翻译：

---

基于深度学习的物联网（IoT）通信异常检测的绿色能源高效路由

当前，基于绿色物联网（IoT）的能源感知网络在传感技术中扮演着重要的角色。物联网的发展对医疗，智能城市，交通等多个应用领域产生了重大影响。传感器节点的指数级增长可能会导致能源消耗增加。因此，将绿色媒体网络中的环境影响最小化对于研究人员和商人都是一个具有挑战性的问题。能源效率和安全性在物联网应用程序设计中仍然至关重要。本文针对物联网应用提出了一种基于DL的异常检测（GEER-DLAD）技术的新型绿色节能路由。提出的模型使IoT设备能够有效利用能源，从而增加网络跨度。GEER-DLAD技术执行错误有损压缩（ELC）技术，以减少网络上的数据通信量。此外，飞蛾群优化算法被用于网络中路由的最优选择。此外，DLAD过程通过递归神经网络长期短期记忆（RNN-LSTM）模型进行，以检测IoT通信网络中的异常情况。进行了详细的实验验证过程，结果确保了GEER-DLAD模型在能效和检测性能方面的改进。DLAD过程通过递归神经网络长期短期记忆（RNN-LSTM）模型进行，以检测IoT通信网络中的异常情况。进行了详细的实验验证过程，结果确保了GEER-DLAD模型在能效和检测性能方面的改进。DLAD过程通过递归神经网络长期短期记忆（RNN-LSTM）模型进行，以检测IoT通信网络中的异常情况。进行了详细的实验验证过程，结果确保了GEER-DLAD模型在能效和检测性能方面的改进。