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.

Efficient recovery in smart grids is critical to minimize outages and maintain stability. This paper addresses the backup power scheduling problem using Deep Reinforcement Learning (DRL). By modeling the recovery process as a Markov Decision Process, we propose a Deep Q-Learning (DQN) solution that dynamically activates backup power units and selects power nodes for repair. Simulation results on a standard test system demonstrate that our method reduces recovery time, improves resource utilization, and enhances grid stability compared to heuristic approaches.

Efficient post-outage recovery in smart grids is critical for minimizing service disruption, reducing recovery costs, and maintaining system stability. This paper formulates the backup power scheduling problem during recovery process as a Markov Decision Process (MDP), and employs cooperative multi-agent Deep Q-Networks (DQN) to jointly coordinate the activation of backup power units and the prioritization of damaged power nodes for repair. Unlike traditional heuristic or static methods, the proposed method adapts in real time to evolving grid conditions and captures complex interdependencies between the power and communication networks. Simulation results on different test systems demonstrate that the proposed method significantly reduces recovery time, conserves limited backup power, and enhances grid resilience compared to baseline strategies.

We study the impact of coupling between the communication and the power networks as it affects a SCADA-based preventive control system. Today power grids use power lines to carry control information between components in the grid and a control center using power line carrier communication (PLCC). Thus a failure in the power grid will cause a failure in the control network and may reduce the capability of preventive control that in turn increases the risk of cascading failures. We pose the problem of allocating a limited number of non-PLCC communication links (e.g., microwave links) that are immune to failures in the power grid to maximize our controllability over the grid under power system failures, so as to maximize the total demand served at the end of cascade. By formulating the problem as a nonlinear integer programming problem, we establish its hardness and identify a generic heuristic that can find an approximate solution within controllable time. We further develop a domain-specific heuristic that utilizes both graph-theoretic and power system information to achieve similar performance as the generic heuristic at a much lower computational complexity. Our evaluations based on a 2, 383-bus Polish system demonstrate that only a few non-PLCC links, when placed correctly, can substantially improve the robustness of the grid as measured by the total demand served at the end of cascade.

Mobile edge computing provides the opportunity for wireless users to exploit the power of cloud computing without a large communication delay. To serve data-intensive applications (e.g., video analytics, machine learning tasks) from the edge, we need, in addition to computation resources, storage resources for storing server code and data as well as network bandwidth for receiving user-provided data. Moreover, due to time-varying demands, the code and data placement needs to be adjusted over time, which raises concerns of system stability and operation cost. In this paper, we address these issues by proposing a two-time-scale framework that jointly optimizes service (code and data) placement and request scheduling, while considering storage, communication, computation, and budget constraints. First, by analyzing the hardness of various cases, we completely characterize the complexity of our problem. Next, we develop a polynomial-time service placement algorithm by formulating our problem as a set function optimization, which attains a constant-factor approximation under certain conditions. Furthermore, we develop a polynomial-time request scheduling algorithm by computing the maximum flow in a carefully constructed auxiliary graph, which satisfies hard resource constraints and is provably optimal in the special case where requests have homogeneous resource demands. Extensive synthetic and trace-driven simulations show that the proposed algorithms achieve 90% of the optimal performance.

Mobile edge computing allows wireless users to exploit the power of cloud computing without the large communication delay. To serve data-intensive applications (e.g., augmented reality, video analytics) from the edge, we need, in addition to CPU cycles and memory for computation, storage resource for storing server data and network bandwidth for receiving user-provided data. Moreover, the data placement needs to be adapted over time to serve time-varying demands, while considering system stability and operation cost. We address this problem by proposing a two-time-scale framework that jointly optimizes service (data & code) placement and request scheduling, under storage, communication, computation, and budget constraints. We fully characterize the complexity of our problem by analyzing the hardness of various cases. By casting our problem as a set function optimization, we develop a polynomial-time algorithm that achieves a constant-factor approximation under certain conditions. Extensive synthetic and trace-driven simulations show that the proposed algorithm achieves 90% of the optimal performance.