A DRL-Based Scheduler for FaaS in Smart Grids: Balancing URLLC Reliability - mMTC Connectivity

The smart grid increasingly relies on edge computing and serverless paradigms to support a diverse range of applications with strict latency, reliability, and scalability demands. Function-as-a-Service (FaaS) offers a lightweight, event-driven model ideal for deploying distributed smart grid functions. However, existing FaaS platforms are not equipped fully to handle the conflicting quality-of-service (QoS) requirements of ultra-reliable low-latency communication (URLLC) and massive machine-type communication (mMTC), which are two dominant traffic classes in modern smart grid environments.This work introduces a Deep Reinforcement Learning (DRL)-based scheduler for QoS-aware FaaS orchestration in the smart grid edge-cloud continuum. By integrating a bi-objective placement strategy into the open-source Fission framework atop Kubernetes, our approach minimizes latency and service-level objective (SLO) violations for URLLC functions, while preventing node congestion and promoting balanced mMTC load distribution.The function placement problem is modeled as a Markov Decision Process (MDP), where node selection is guided by a reward function that incorporates an exponential latency cost, soft reliability penalties, and real-time connectivity metrics. Training is performed using realistic smart grid workloads on the Grid’5000 testbed.Experimental results demonstrate the effectiveness of the proposed scheduler in enhancing URLLC compliance, reducing latency, and maintaining efficient mMTC load distribution, all while introducing minimal overhead. These findings highlight the potential of intelligent, low-cost serverless orchestration for next-generation smart grid infrastructures.