Aug 2026· International Conference on Circuit, Power and Computing Technologies· pp. 1615-1620· 0 citations· 24 references
Abstract
Kubernetes Horizontal Pod Autoscaler(HPA) and other existing auto-scaling solutions that respond reactively to demand experience significant delays in provisioning and inefficiencies when responding to sudden workload spikes. This paper proposes a new Real-Time Workload Monitoring-Based Intelligent Auto-Scaling Framework that uses a hybrid time-series forecasting model to proactively manage cloud computing resources. Specifically, it combines periodicity detection with Prophet-based models and long-term dependence capture via Long Short-Term Memory (LSTM) networks to provide advanced notice of CPU and memory requirements before load surges occur. The results of this approach were compared against traditional reactive auto-scaling methods and demonstrated that it significantly reduced scaling latencies, minimized service level agreement (SLA) violations, and optimized resource utilization during load surges.
Kubernetes has become the dominant orchestration substrate for cloud-native applications, yet its native autoscaling mechanisms remain primarily reactive, threshold-driven, and limited in their ability to anticipate workload volatility before service-level agreement violations occur. Modern microservice systems exhibit non-linear interactions among request arrival rates, queueing delays, CPU saturation, memory pressure, network variability, pod cold-start latency, and downstream dependency bottlenecks. These characteristics make single-metric autoscaling policies insufficient for latency-sensitive workloads operating under strict service-level objectives. This paper proposes a Transformer-Based Multi-Signal Predictive Autoscaling framework for SLA-aware resource management in Kubernetes-orchestrated cloud-native environments. The proposed framework integrates heterogeneous observability signals, multi-horizon time-series forecasting, uncertainty-aware decision logic, and Kubernetes-native actuation to allocate resources before overload conditions materialize. Unlike conventional Horizontal Pod Autoscaler configurations that respond after resource utilization crosses predefined thresholds, the proposed approach forecasts near-future demand and performance risk using a Transformer encoder architecture designed to learn long-range dependencies, temporal seasonality, burst behavior, and cross-metric interactions. The framework translates predicted workload and latency risk into safe scaling actions through policy constraints that consider replica bounds, cooldown windows, pod readiness delays, cost budgets, and SLA violation probability. The paper develops the conceptual architecture, methodological workflow, evaluation metrics, and analytical discussion necessary for empirical implementation. The study argues that SLA-aware predictive autoscaling should be treated not merely as a forecasting task but as an integrated control problem involving observability quality, model calibration, decision governance, and runtime safety. The proposed model contributes to cloud resource management research by aligning deep temporal learning with Kubernetes operational semantics and by providing a structured pathway toward more reliable, efficient, and self-adaptive cloud-native platforms.
Nilesh Mutyam· International Journal of Art...· 0 citations
A hybrid congestion-aware autoscaling framework for serverless platforms inspired by TCP slow-start and congestion control principles is proposed, which significantly improves latency performance, scalability, and resource efficiency in serverless environments.
Mohammad Tari, Mostafa Ghobayee-Arani, Jafar Pouramini· International Journal of Clo...· 0 citations
AutoSLO is presented, a latency-SLO-aware workload management framework for multi-cluster cloud data warehouses that successfully meets latency SLOs of varying strictness, reducing cost by a mean of 26.4% compared to the per-scenario next-best baseline.
Markos Markakis, T. Kraska· arXiv.org· 0 citations
Efficient cluster scheduling requires reliable forecasts of resource demand, yet production workloads are heterogeneous, bursty, and strongly time-dependent. Using the Google Cluster-Usage Traces v3, we study leakage-safe prediction of three scheduling-relevant metrics: mean CPU demand, normalized memory pressure (average memory relative to assigned memory), and tail CPU demand (p95) as a burst-risk indicator. We develop a preprocessing and evaluation protocol that explicitly addresses two common threats to validity in trace-based learning: post-execution feature leakage (e.g., usage-derived fields) and identity leakage from random splits when recurring workloads appear in both training and test sets. Under time-ordered and gap-based splits, we compare gradient-boosted tree models (LightGBM) against strong history-only baselines (LastSeen and EMA) and perform a cold-start analysis by evaluating the first K occurrences of each workload entity. Results reveal a clear regime shift: for warm, recurring workloads, simple entity-history predictors achieve near-optimal accuracy and consistently outperform learned models; however, in cold-start settings where history is unavailable, LightGBM substantially improves CPU mean and tail forecasts (e.g., large gains in R2 for first-occurrence entities). These findings support a practical scheduling strategy: a hybrid, regime-aware policy that uses machine learning (ML) as a cold-start fallback and switches to lightweight history-based prediction as observations accumulate.
Kalab M. Kiros, Jinwei Liu· IEEE International Conferenc...· 0 citations
SAGF (SLO-Aware Graph Forecasting), an integrated prediction-and-control framework for proactive autoscaling, encodes six per-service metrics on a spatio-temporal call graph, predicts per-service SLO risk via GCN with temporal gating, and feeds these scores to a constrained RL controller for dependency-aware scaling.
Kang Yang, Feng Wang, Ruili Jiang· 2026 8th International Confe...· 2 citations
This work outlines AutoSLO, a latency-SLO-aware work-load management framework for multi-cluster cloud data ware-houses that includes a periodic Policy Tuner that proactively plans resources using workload fore-casts, an SLO-aware reactive Autoscaler that adjusts the active cluster set based on the observed workload, and an online Query Router that reacts to concurrent query load when routing.
Markos Markakis, T. Kraska· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
