System identification in control theory aims to approximate dynamical systems from trajectory data. While neural networks have demonstrated strong predictive accuracy, they often fail to preserve critical physical properties such as stability and typically assume stationary dynamics, limiting their applicability under distribution shifts. Existing approaches generally address either stability or adaptability in isolation, lacking a unified framework that ensures both. We propose LILAD (Learning In-Context Lyapunov-stable Adaptive Dynamics), a novel framework for system identification that jointly guarantees adaptability and stability. LILAD simultaneously learns a dynamics model and a Lyapunov function through in-context learning (ICL), explicitly accounting for parametric uncertainty. Trained across a diverse set of tasks, LILAD produces a stability-aware, adaptive dynamics model alongside an adaptive Lyapunov certificate. At test time, both components adapt to a new system instance using a short trajectory prompt, which enables fast generalization. To rigorously ensure stability, LILAD also computes a state-dependent attenuator that enforces a sufficient decrease condition on the Lyapunov function for any state in the new system instance. This mechanism extends stability guarantees even under out-of-distribution and out-of-task scenarios. We evaluate LILAD on benchmark autonomous systems and demonstrate that it outperforms adaptive, robust, and non-adaptive baselines in predictive accuracy.

Given the availability of more comprehensive measurement data in modern power systems, reinforcement learning (RL) has gained significant interest in operation and control. Conventional RL relies on trial-and-error interactions with the environment and reward feedback, which often leads to exploring unsafe operating regions and executing unsafe actions, especially when deployed in real-world power systems. To address these challenges, safe RL has been proposed to optimize operational objectives while ensuring safety constraints are met, keeping actions and states within safe regions throughout both training and deployment. Rather than relying solely on manually designed penalty terms for unsafe actions, as is common in conventional RL, safe RL methods reviewed here primarily leverage advanced and proactive mechanisms. These include techniques such as Lagrangian relaxation, safety layers, and theoretical guarantees like Lyapunov functions to rigorously enforce safety boundaries. This article provides a comprehensive review of safe RL methods and their applications across various power system operations and control domains, including security control, real-time operation, operational planning, and emerging areas. It summarizes existing safe RL techniques, evaluates their performance, analyzes suitable deployment scenarios, and examines algorithm benchmarks and application environments. This article also highlights real-world implementation cases and identifies critical challenges such as scalability in large-scale systems and robustness under uncertainty, providing potential solutions and outlining future directions to advance the reliable integration and deployment of safe RL in modern power systems.

This paper addresses the problem of Neural Network (NN) based adaptive stability certification in a dynamical system. The state-of-the-art methods, such as Neural Lyapunov Functions (NLFs), use NN-based formulations to assess the stability of a non-linear dynamical system and compute a Region of Attraction (ROA) in the state space. However, under parametric uncertainty, if the values of system parameters vary over time, the NLF methods fail to adapt to such changes and may lead to conservative stability assessment performance. We circumvent this issue by integrating Model Agnostic Meta-learning (MAML) with NLFs and propose meta-NLFs. In this process, we train a meta-function that adapts to any parametric shifts and updates into an NLF for the system with new test-time parameter values. We demonstrate the stability assessment performance of meta-NLFs on some standard benchmark autonomous dynamical systems.

Foundational Large Language Models (LLMs) such as GPT-3.5-turbo allow users to refine the model based on newer information, known as "fine-tuning". This paper leverages this ability to analyze AC-DC converter behaviors, focusing on the ripple current in DC-link capacitors. Capacitors degrade faster under high ripple currents, complicating life monitoring and necessitating preemptive replacements. Using minimal invasive noisy hardware measurements from a full bridge rectifier and 90W Power Factor Correction (PFC) boost converter, an LLM-based models to predict ripple content in DC-link currents was developed which demonstrated the LLMs’ ability for near-accurate predictions. This study also highlights data requirements for precise nonlinear power electronic circuit parameter predictions to predict component degradation without any additional sensors. Furthermore, the proposed framework could be extended to any non-linear function mapping problem as well as estimating the capacitor Equivalent Series Resistance (ESR).

This article presents a use-inspired perspective of the opportunities and challenges in a massively digitized power grid. It argues that the intricate interplay of data availability, computing capability, and artificial intelligence (AI) algorithm development are the three key factors driving the adoption of digitized solutions in the power grid. The impact of these three factors on critical functions of power system operation and planning practices is reviewed and illustrated with industrial practice case studies. Open challenges and research opportunities for data, computing, and AI algorithms are articulated within the context of the power industry’s tremendous decarbonization efforts.

This article presents considerations toward an information and control architecture for future electric energy systems driven by massive changes resulting from the societal goals of decarbonization and electrification. This article describes the new requirements and challenges of an extended information and control architecture that needs to be addressed for continued reliable delivery of electricity. It identifies several new actionable information and control loops, along with their spatial and temporal scales of operation, which can together meet the needs of future grids and enable deep decarbonization of the electricity sector. The present architecture of electric power grids designed in a different era is thereby extensible to allow the incorporation of increased renewables and other emerging electric loads.

One of the major factors that lead to energy losses for utility distribution systems is electricity or energy theft. Energy theft is tampering with smart meter reading to reduce customer energy usage and reduce electricity bills. A thief customer tends to consume more energy and hence, the theft negatively affects the power supply quality in the form of transformer overload, voltage unbalance, and voltage drop on system buses. Meanwhile, it also causes great economic losses for the business of electric utility. In order to enable efficient energy theft detection, data-driven approaches including utilizing trained deep neural networks are proposed in this paper. The machine learning approaches can detect energy theft involving stealthy connections or meter tampering at the level of smart meters or aggregated levels. In this work, the detection effectiveness of different approaches is evaluated on real case study data at the end consumer level. The challenges of class imbalance and the missing values (around 25% of the whole fields) are addressed in the LSTM-based methodology. In this paper, results are obtained on real energy consumption data to show the higher performance of the proposed solutions compared to previously presented work.

The traditional electric power grid is moving toward smart grid, and with the advent of smart grids, a lot of data is generated in high volumes, velocity and variety. This brings several challenges with real time processing to get meaningful information for enhancing the benefits of smart grid. Furthermore, the application of short-term load forecasting poses additional challenges of being highly uncertain and volatile due to different load profiles. This paper conducts a study on the demand side management and load forecasting in electric power grids with help of the historical data obtained from smart grid. Machine learning models are developed using deep learning to ensure significant improvement in forecast accuracy when compared to benchmark Auto-Regressive Integrated Moving Averages ARIMA analysis. The short-term load forecast data has been merged with weather data from Application Program Interface (API). The discussed system uses an autonomous feedback loop to consider the historical load values as features for training and testing. This paper also applies deep learning methods like pooling based recurrent neural networks which could solve the curse of dimensionality that usually exists with increasing layers in traditional neural network methods. The paper proposes an averaging regression ensembles model for short-term load forecast.

No abstract available.

This paper surveys major technical challenges for power system operations in support of large-scale wind energy integration. The fundamental difficulties of integrating wind power arise from its high inter-temporal variation and limited predictability. The impact of wind power integration is manifested in, but not limited to, scheduling, frequency regulations, and system stabilization requirements. Possible alternatives are suggested for a more reliable and cost-effective power system operation. New computationally efficient methods for improving system performances by using prediction and operational interdependencies over different time horizons remain critical open research problems.

We study the problem of short term wind speed prediction, which is a critical factor for effective wind power generation. This is a challenging task due to the complex and stochastic behavior of the wind environment. Observing various periods in the wind speed time series present different patterns, we suggest a nonlinear adaptive framework to model various hidden dynamic processes. The model is essentially data driven, which leverages non-parametric Heteroscdastic Gaussian Process to model relevant patterns for short term prediction. We evaluate our model on two different real world wind speed datasets from National Data Buoy Center. We compare our results to state-of-arts algorithms to show improvement in terms of both Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE).

The study of Cyber-Physical System (CPS) has been an active area of research. Internet Data Center (IDC) is an important emerging Cyber-Physical System. As the demand on Internet services drastically increases in recent years, the power used by IDCs has been skyrocketing. While most existing research focuses on reducing power consumptions of IDCs, the power management problem for minimizing the total electricity cost has been overlooked. This is an important problem faced by service providers, especially in the current multi-electricity market, where the price of electricity may exhibit time and location diversities. Further, for these service providers, guaranteeing quality of service (i.e. service level objectives-SLO) such as service delay guarantees to the end users is of paramount importance. This paper studies the problem of minimizing the total electricity cost under multiple electricity markets environment while guaranteeing quality of service geared to the location diversity and time diversity of electricity price. We model the problem as a constrained mixed-integer programming and propose an efficient solution method. Extensive evaluations based on real-life electricity price data for multiple IDC locations illustrate the efficiency and efficacy of our approach.

This paper proposes modeling the rapidly evolving energy systems as cyber-based physical systems. It introduces a novel cyber-based dynamical model whose mathematical description depends on the cyber technologies supporting the physical system. This paper discusses how such a model can be used to ensure full observability through a cooperative information exchange among its components; this is achieved without requiring local observability of the system components. This paper also shows how this cyber-physical model is used to develop interactive protocols between the controllers embedded within the system layers and the network operator. Our approach leads to a synergistic framework for model-based sensing and control of future energy systems. The newly introduced cyber-physical model has network structure-preserving properties that are key to effective distributed decision making. The aggregate load modeling that we develop using data mining techniques and novel sensing technologies facilitates operations of complex electric power systems.

This paper addresses potential benefits of applying model predictive control (MPC) to solving the energy dispatch problem in electric energy systems with many intermittent renewable resources. Based on predicting the output from the intermittent resources, this paper introduces a look-ahead optimal control algorithm for dispatching the available generation with the objective of minimizing the total production cost. This method is compared with the static economic dispatch which treats intermittent resources as uncertain negative loads. We suggest that the proposed MPC approach could lower the total generation cost by directly dispatching the output from the renewable resources in order to compensate temporal load variations over pre-defined time horizons. A small 12-bus power system comprising five generators is simulated to illustrate potential benefits from a look-ahead dispatch of both intermittent and more conventional power plants. The proposed method is directly applicable to managing systems with large presence of wind and photovoltaic resources.