We present GreenCloud-RL, a formally defined scheduler for multi-cloud fleets that jointly optimizes carbon emissions, operational cost, and service-level agreement (SLA) risk. The scheduling problem is modeled as a constrained Markov decision process (CMDP) in which expected cost–carbon reward is maximized subject to aggregate SLA-risk and power-cap constraints. The framework integrates (i) a physics-informed DVFS power model, (ii) queueing-theoretic latency predictors, (iii) probabilistic short-term forecasts of regional grid carbon intensity and electricity price with uncertainty penalties, and (iv) a dual-variable actor–critic algorithm that provably enforces constraint satisfaction online. We analyze the algorithm’s convergence under bounded rewards and provide distributed complexity bounds for large-scale multi-cloud control. Empirical evaluation on production-like workloads shows that GreenCloud-RL reduces SLA-violation rate by 37.6% and power-cap violations by 53.8%, while lowering mean tardiness to 1.9 s and improving throughput by 4.2% compared with strong baselines. A region×regime analysis (load ∈ {low, medium, high}; grid ∈ {clean, neutral, dirty}) demonstrates consistent reductions in both cost and carbon emissions without degrading SLA satisfaction. Post-hoc calibration improves reliability (ECE 4.8%→1.7%, lower Brier score), enabling trustworthy on-time probability estimates for risk-aware admission and tenant-tier guarantees. Scalability tests show a p95 scheduling latency of ≈41 ms at 100k jobs, ≈0.25 ms inference per decision, modest CPU/GPU overhead, and ≈5 s controller failover. These results establish, both theoretically and empirically, that multi-objective optimization of carbon, cost, and reliability is achievable in production-scale cloud environments while maintaining contractual SLA guarantees. 

Cloud platforms generate massive API access logs, where abnormal patterns may indicate security breaches, insider threats, or compromised credentials, demanding intelligent and automated anomaly detection mechanisms. Conventional approaches employ segmentation, statistical profiling, clustering, recurrent networks, and supervised classifiers to model sequential API behavior and distinguish normal activities from malicious deviations. These techniques generally achieve high detection accuracy and improved threat visibility, enhancing cybersecurity monitoring systems while reducing manual auditing efforts in large-scale distributed cloud environments. However, they struggle with evolving attack patterns, high false-positive rates, limited temporal dependency modelling, data imbalance, and poor generalization across heterogeneous cloud infrastructures. This study proposes a self-supervised Temporal Convolutional Network with adaptive anomaly scoring, achieving robust sequential modelling, reduced false alarms, and improved detection stability in cloud APIs. A self-supervised Temporal Convolutional Network models sequential API behavior using causal dilated convolutions and adaptive scoring, enabling accurate, scalable, and real-time cloud anomaly detection.