Cost-effective intelligent building: Energy management system using machine learning and multi-criteria decision support

Enhancing cost-effective energy management in buildings is critical for achieving sustainability goals and addressing the challenges posed by rising energy use, which is a major concern for energy policy frameworks worldwide. This study is a trailblazer in using multi-criteria decision-making (MCDM) methodologies for the real-time operational optimisation of building energy systems. Data collection and pre-processing, feature extraction, feature selection, classification, trust authentication, encryption, and decryption are among the techniques used in this approach. Pre-processing procedures for the raw data include feature encoding, dimension reduction, and normalisation approaches. The Hybrid Grey Level Co-occurrence Matrix Fast Fourier Transform (HGLCM-FFT) method is used for feature extraction. Filter-based methods are used for feature selection, including IG, CS, symmetric uncertainty, and gain ratio. The Hierarchical Gradient Boosted Isolation Forest (HGB-IF) technique is used for the classification. Distributed Adaptive Trust-Based Authentication (DATBA), a security architecture in distributed cloud environments, uses trust authentication. The Particle Swarm Optimized Symmetrical Blowfish (PSOSB) method is used for encryption and decryption.The proposed framework not only ensures robust data security but also provides actionable insights for energy efficiency improvements, aligning with broader economic and environmental objectives. The suggested work is implemented using OS Python - 3.9.6; the performance of the proposed model is Attack Detection Rate, False alarm rate, True positive rate, Network usage, CPU usage, Encryption time, encryption time, and Throughput.