Energy-Efficient Deep Learning via Compression: Green AI

With the rapid growth of artificial intelligence (AI), deep learning models are becoming more complex and requiresignificant computing power, memory, and energy. This makes it difficult to deploy them on devices with limited resources, suchas smartphones, embedded systems, and edge devices. To address this challenge, model compression techniques have emerged asa key solution. These methods reduce the size and computational cost of AI models while keeping their performance close to thatof the original models. This paper explores four widely used model compression techniques: pruning, quantization, knowledgedistillation, and low-rank factorization. Each technique is explained in terms of how it works, its advantages, and the trade-offsit brings. A special focus is placed on pure compression strategies, which avoid external indexing or lookup tables and are bettersuited for simple and energy-efficient systems. A case study using a convolutional neural network (CNN) shows that combiningpruning and quantization can reduce model size by more than 80% and speed up inference time by 30% with only a small lossin accuracy. The study also highlights key metrics for evaluating compressed models, including memory usage, speed, andaccuracy. Finally, the paper discusses real-world applications in mobile devices, healthcare, and autonomous systems, along withfuture directions such as automated compression tools and energy-aware training. Overall, this research supports thedevelopment of more accessible, scalable, and eco-friendly AI by making models lighter and more efficient.