Energy-Aware Intelligent Computing Framework for Sustainable AI Workloads in Next-Generation Smart Systems
DOI:
https://doi.org/10.63503/j.ijssic.2025.201Keywords:
Energy-Aware Computing, Hybrid CNN-LSTM, Transformer Scheduling, Intelligent Resource Allocation, Deep Learning, Cloud SustainabilityAbstract
The intelligent computing infrastructures based on artificial intelligence (AI) have substantially increased the energy usage, lag times in computation, and costs of sustainability due to the exponential rise in the workloads. The classical models of workload management put much emphasis on predictive accuracy but ignore resource-awareness, with the net effect of inefficient usage of power and poor system responsiveness. This paper puts forward an Energy-Aware Hybrid CNN-LSTM-Transformer (EA-HCLT) architecture that would allow sustainable computing through the combination of workload prediction, smart scheduling and adaptive carving of model pruning to dynamic environments. The framework utilises workload prediction using hybrid learning/deep learning in real-time resource monitoring to optimally place computers to execute computations and also optimally use energy at maximum precision. As a validation of the effectiveness, EA-HCLT is compared to two popular models: Random Forest Workload Predictor (RF-WP) and Standard LSTM Scheduler (S-LSTM) based on the usage of synthetic workload and runtime workload datasets in terms of CPU, memory, network throughput, and accelerator utilisation. The overall analysis of the proposed approach in terms of accuracy, RMSE, latency, energy usage, sustainability index, and multi-objective cost reveal that the proposed solution provides a considerable improvement, yielding 14.8 percentage points higher accuracy, 19% reduced decision latency, 26.9% decreased energy usage, 17.5% higher sustainability index as opposed to S-LSTM. The results justify the supportability and scalability of the suggested EA-HCLT design and emphasise the significance of energy-conscious strategies of the next generation smart systems that are going to work within environmental and resource constraints.
References
[1] Ghaseminya, M. M., Eslami, E., Shahzadeh Fazeli, S. A., Abouei, J., Abbasi, E., & Karbassi, S. M. (2025). Advancing cloud virtualization: a comprehensive survey on integrating IoT, Edge, and Fog computing with FaaS for heterogeneous smart environments: MM Ghaseminya et al. The Journal of Supercomputing, 81(14), 1303. https://doi.org/10.1007/s11227-025-07799-2
[2] Mouhim, S. A. N. A. A., & Lachhab, F. A. D. W. A. (2025). Towards a context awareness system using IoT, AI, and big data technologies. IEEE Access. https://doi.org/10.1109/ACCESS.2025.3546865
[3] Arroba, P., Buyya, R., Cárdenas, R., Risco‐Martín, J. L., & Moya, J. M. (2024). Sustainable edge computing: Challenges and future directions. Software: Practice and Experience, 54(11), 2272-2296. https://doi.org/10.1002/spe.3340
[4] Lalar, S., Kumar, T., Kamboj, S., & Kumar, R. (2024). Security challenges and solutions in cloud, fog, and edge computing for sustainable development. In Cloud and Fog Optimization-based Solutions for Sustainable Developments (pp. 178-200). CRC Press. https://doi.org/10.1201/9781003494430
[5] Krishnan, R., & Durairaj, S. (2024). Reliability and performance of resource efficiency in dynamic optimization scheduling using multi-agent microservice cloud-fog on IoT applications. Computing, 106(12), 3837-3878. https://doi.org/10.1007/s00607-024-01301-1
[6] Hussain, H., Tamizharasan, P. S., & Rahul, C. S. (2022). Design possibilities and challenges of DNN models: a review on the perspective of end devices. Artificial Intelligence Review, 55(7), 5109-5167 https://doi.org/10.1007/s10462-022-10138-z
[7] Dritsas, E., & Trigka, M. (2025). Machine Learning in Intelligent Networks: Architectures, Techniques, and Use Cases. IEEE Access. https://doi.org/10.1109/ACCESS.2025.3577968
[8] Alomar, K., Aysel, H. I., & Cai, X. (2025). CNNs, RNNs and Transformers in human action recognition: a survey and a hybrid model. Artificial Intelligence Review, 58(12), 1-44. https://doi.org/10.1007/s10462-025-11388-3
[9] Li, W., & Law, K. E. (2024). Deep learning models for time series forecasting: A review. IEEE Access, 12, 92306-92327. https://doi.org/10.1109/ACCESS.2024.3422528
[10] Abdel Raouf, A. E., Abo‐alian, A., & Badr, N. L. (2021). A predictive replication for multi‐tenant databases using deep learning. Concurrency and Computation: Practice and Experience, 33(13), e6226. https://doi.org/10.1002/cpe.6226
[11] Moradi, H., Wang, W., & Zhu, D. (2021). Online performance modeling and prediction for single-VM applications in multi-tenant clouds. IEEE Transactions on Cloud Computing, 11(1), 97-110. https://doi.org/10.1109/TCC.2021.3078690
[12] Li, A., Xiao, F., Zhang, C., & Fan, C. (2021). Attention-based interpretable neural network for building cooling load prediction. Applied Energy, 299, 117238. https://doi.org/10.1016/j.apenergy.2021.117238
[13] Iqbal, N., Khan, A. N., Rizwan, A., Qayyum, F., Malik, S., Ahmad, R., & Kim, D. H. (2022). Enhanced time-constraint aware tasks scheduling mechanism based on predictive optimization for efficient load balancing in smart manufacturing. Journal of manufacturing systems, 64, 19-39. https://doi.org/10.1016/j.jmsy.2022.05.015
[14] Hudda, S., & Haribabu, K. (2025). A review on WSN based resource constrained smart IoT systems. Discover Internet of Things, 5(1), 56. https://doi.org/10.1007/s43926-025-00152-2
[15] Shouran, M., Alenazi, M., Almutairi, S., & Alajmi, M. (2025). Hybrid Feature Extraction and Deep Learning Framework for Power Transformer Fault Classification–A Real-World Case Study. IEEE Access. https://doi.org/10.1109/ACCESS.2025.3608658
[16] Sanjalawe, Y., Al-E’mari, S., Fraihat, S., & Makhadmeh, S. (2025). AI-driven job scheduling in cloud computing: a comprehensive review. Artificial Intelligence Review, 58(7), 197. https://doi.org/10.1007/s10462-025-11208-8
[17] Yuan, H., Bi, J., Li, S., Zhang, J., & Zhou, M. (2024). An improved LSTM-based prediction approach for resources and workload in large-scale data centers. IEEE Internet of Things Journal, 11(12), 22816-22829. https://doi.org/10.1109/JIOT.2024.3383512
[18] Yu, Q., Yang, G., Wang, X., Shi, Y., Feng, Y., & Liu, A. (2025). A review of time series forecasting and spatio-temporal series forecasting in deep learning: Q. Yu et al. The Journal of Supercomputing, 81(10), 1160. https://doi.org/10.1007/s11227-025-07632-w
[19] Yazdanian, P., & Sharifian, S. (2021). E2LG: a multiscale ensemble of LSTM/GAN deep learning architecture for multistep-ahead cloud workload prediction. The Journal of Supercomputing, 77(10), 11052-11082. https://doi.org/10.1007/s11227-021-03723-6
[20] Nagesh, C., Jayudu, T. V. N., Rao, N. S., Hariprasad, E., Naresh, A., & Balaji, C. (2025, August). Predicting Market Volatility and Risk Analysis with ESG Factors: A Hybrid Approach Using LSTM and ARIMA. In 2025 9th International Conference on Inventive Systems and Control (ICISC) (pp. 102-107). IEEE. https://doi.org/10.1109/ICISC65841.2025.11187620
