With the growth of the internet of things (IoT) smart objects, managing these objects becomes a very important challenge, to know the total number of interconnected objects on a heterogeneous network, and if they are functioning correctly; the use of IoT objects can have advantages in terms of comfort, efficiency, and cost. In this context, the identification of IoT objects is the first step to help owners manage them and ensure the security of their IoT environments such as smart homes, smart buildings, or smart cities. In this paper, to meet the need for IoT object identification, we have deployed an intelligent environment to collect all network traffic traces based on a diverse list of IoT in real-time conditions. In the exploratory phase of this traffic, we have developed learning models capable of identifying and classifying connected IoT objects in our environment. We have applied the six supervised machine learning algorithms: support vector machine, decision tree (DT), random forest (RF), k-nearest neighbors, naive Bayes, and stochastic gradient descent classifier. Finally, the experimental results indicate that the DT and RF models proved to be the most effective and demonstrate an accuracy of 97.72% on the analysis of network traffic data and more particularly information contained in network protocols. Most IoT objects are identified and classified with an accuracy of 99.21%.

A Smart campus increasingly operates on the basis of data-driven operations, but an increasing demand for energy puts their control over costs and sustainability at risk. This study addresses the challenge of anticipating and managing energy consumption peaks in multi-campus environments by proposing a hybrid framework that combines advanced time-series forecasting models with a large language model (LLM)-driven multi-agent system. Based on the UNICON dataset, LSTM, CNN, GRU, and a combination architecture are trained and compared in terms of MAE and RMSE. The hybrid configuration achieves the greatest forecasting results by returning the minimum loss values. For the identification of critical periods, we employed a strategy based on median thresholding, which offers a categorization into low, normal, and extreme category, allowing the targeting of peak mitigation actions. We also introduce a multi-agent system based on the LLM, including the data aggregator, the forecaster, and the policy advisor, which create actionable policies informed by context. We also compare LLMs (Qwen-2.5, Gemma-2, Phi-4, Mistral, Llama-3.3) in terms of context accuracy, response relevance, semantic similarity, and retrieval/recall accuracy and fidelity, with Llama-3.3 achieving the best overall results. This framework has shown great potential, not only for energy consumption forecasting but also for developing precise policies on how to effectively manage energy consumption peaks.