Artificial intelligence (AI) research and market have grown rapidly in the last few years, and this trend is expected to continue with many potential advancements and innovations in this field. One of the emerging AI research directions is Distributed Artificial Intelligence (DAI). It has been motivated by technological advances in communication, networking, and hardware, together with the nature of data being generated from connected, distributed, and diverse objects. DAI is expected to create a fertile environment for innovative, advanced, robust, and scalable approaches for AI supporting the vision of smart societies. In this paper, we explore state of the art on DAI and identify the opportunities and challenges of provisioning distributed AI as a service (DAIaaS). We provide a taxonomy and a comprehensive review covering the literature from 2016 to 2022. It comprises various aspects of DAI, including AI workflow, distribution paradigms, supporting infrastructure, management techniques, and applications. Based on the gained insights from the conducted review, we propose Imtidad, a framework for provisioning DAIaaS over the cloud, fog, and edge layers. We refine this framework and propose the Imtidad software Reference Architecture (RA) for designing and deploying DAI services. In addition, we extended the framework and developed a future networking infrastructure transformation framework, as it is one of the main enablers for DAI. This framework and RA can be used as guidance facilitating the transition to the future DAI, where DAI is decoupled from the design and development of smart applications. This paper, including the proposed framework, RA, taxonomy, and detailed review, is expected to have an extensive impact on DAI research and accelerate innovations in this area.

Attention-based models have been very effective in identifying important lagged variables for multivariate time series (MTS) forecasting applications. However, current attention-based models only provide static weights and do not consider the dynamic nature of predictions for multistep predictions of heterogeneous MTS. To address these limitations, this paper proposes a novel multidimensional dynamic attention (MDA) model for computing lagged variable importance. It incorporates a dynamic representation learner unit and considers multiple attention calculations to account for prediction dynamics, temporal information, and variable relations. Extensive experiments with both synthetic and real-world data demonstrate the effectiveness of the MDA model. It outperforms existing methods in the literature for sequence-to-sequence prediction of heterogeneous MTS in most cases and accurately identifies important features. MDA demonstrates enhancements up to 33% with real-world datasets. These findings demonstrate that the MDA model is a promising approach to MTS forecasting. The proposed attention mechanism can be utilised for other tasks related to MTS analysis beyond just forecasting, potentially enhancing the performance and interpretability of various MTS applications.

Latent sector errors (LSEs) in disk drives cause significant outages, data loss, and unreliability in large-scale cloud storage systems, posing not only technical challenges but also environmental concerns in the context of carbon recycling. Predicting LSEs can help avoid these problems and improve cloud reliability, while also contributing to a more sustainable cloud infrastructure. Ensemble classifiers typically outperform individual classifiers for LSE prediction with high accuracy but can lead to underfitting and incurring additional computational cost, complexity, and time and memory consumption. This research addresses this challenge by proposing a twofold solution: optimizing the ensemble diversity of the resulting Random Forest (RF) classifier through accuracy sliding window-based ensemble pruning (SWEP-RF) and using this pruned ensemble to predict LSEs in cloud storage. By effectively predicting and mitigating LSEs, this approach reduces unnecessary energy consumption and carbon emissions associated with data recovery and reprocessing, aligning with carbon recycling goals. SWEP-RF maximizes its lower margin distribution to adapt the RF prediction performance and produce a strong-performing and effective subensemble, further enhancing the overall energy efficiency of cloud systems. Our approach also reduces ensemble size while maintaining high prediction accuracy, leading to more sustainable resource utilization. We evaluate our algorithm using datasets from Baidu Inc and Backblaze datacenters. Experimental results demonstrate that our approach achieves over 98.6% prediction accuracy, a low false alarm rate (FAR) of 0.003%, and extended meantime to data loss (MTTDL) with lead time in advance (LTA) of up to 383.4 Hrs. and 474.3 Hrs., respectively. SWEP-RF outperforms classical models and current state-of-the-art techniques in prediction accuracy, FAR, MTTDL, processing time, memory consumption, and cloud availability, highlighting its significance in not only enhancing cloud storage reliability but also reducing the carbon footprint of cloud services. Our method is a promising solution for enhancing cloud storage reliability through proactive LSE prediction, while addressing the urgent need for sustainable practices and carbon recycling in cloud computing.