To realize efficient and versatile energy management systems for future homes, buildings, and local communities, nano-grid (NG) finds possibility for integrating distributed energy resources. This paper implements the power flow coloring, which gives a unique ID to each power flow between a specific power source and a specific power load. It enables us to design versatile power flow patterns between distributed power sources and loads, taking into account energy availability, cost, and carbon dioxide emission. To implement the power flow coloring, this paper proposes a cooperative distributed control method, where a master-slave role assignment scheme of power sources and a time-slot based feedback control are introduced to cope with power fluctuations while keeping the voltage stability of the NG. Experimental results show the practical feasibility of our proposed method in managing distributed power sources and fluctuating loads.

Electricity theft is one of the challenging problems in smart grids. The power utilities around the globe face huge economic loss due to ET. The traditional electricity theft detection (ETD) models confront several challenges, such as highly imbalance distribution of electricity consumption data, curse of dimensionality and inevitable effects of non-malicious factors. To cope with the aforementioned concerns, this paper presents a novel ETD strategy for smart grids based on theft attacks, long short-term memory (LSTM) and gated recurrent unit (GRU) called TLGRU. It includes three subunits: (1) synthetic theft attacks based data balancing, (2) LSTM based feature extraction, and (3) GRU based theft classification. GRU is used for drift identification. It stores and extracts the long-term dependency in the power consumption data. It is beneficial for drift identification. In this way, a minimum false positive rate (FPR) is obtained. Moreover, dropout regularization and Adam optimizer are added in GRU for tackling overfitting and trapping model in the local minima, respectively. The proposed TLGRU model uses the realistic EC profiles of the Chinese power utility state grid corporation of China for analysis and to solve the ETD problem. From the simulation results, it is exhibited that 1% FPR, 97.96% precision, 91.56% accuracy, and 91.68% area under curve for ETD are obtained by the proposed model. The proposed model outperforms the existing models in terms of ETD.

In today’s power systems, electric vehicles (EVs) constitute a significant factor influencing electricity dynamics, with their important role anticipated in future smart grid systems. An important feature of electric vehicles is their dual capability to both charge and discharge energy to/from their battery storage. Notably, the discharge capability enables them to offer vehicle-to-grid (V2G) services. However, most V2G research focuses on passenger cars, which typically already have their own specific usage purposes and various traveling schedules. This situation may pose practical challenges in providing ancillary services to the grid. Conversely, electric school buses (ESBs) exhibit a more predictable usage pattern, often deployed at specific times and remaining idle for extended periods. This makes ESBs more practical for delivering V2G services, especially when prompted by incentive price signals from grid or utility companies (UC) requesting peak shaving services. In this paper, we introduce a V2G energy sharing model focusing on ESBs in various schools in a single community by formulating the problem as a leader–follower game. In this model, the UC assumes the role of the leader, determining the optimal incentive price to offer followers for discharging energy from their battery storage. The UC aims to minimize additional costs from generating energy during peak demand. On the other hand, schools in a community possessing multiple ESBs act as followers, seeking the optimal quantity of discharged energy from their battery storage. They aim to maximize utility by responding to the UC’s incentive price. The results demonstrate that the proposed model and algorithm significantly aid the UC in reducing the additional cost of energy generation during peak periods by 36% compared to solely generating all electricity independently. Furthermore, they substantially reduce the utility bills for schools by up to 22.6% and lower the peak-to-average ratio of the system by up to 9.5%.

With the rapid development of distributed generators (DGs) and increasing power penetration level of renewable energy sources (RESs), it is a critical issue for any power system to operate safely and continuously in the presence of uncertainty and variability (i.e., power fluctuations) of generated power and demanded power. The introduction of controllable power generators and power storage devices is dispensable for mitigating this problem. To satisfy the power supply–demand balancing requirement, the power flow assignment is essential under power balance constraint. However, due to the physical power limitation constraints of power generators and loads, capacity limitation of power storage devices, and connection arrangement, it is hard to achieve power balance. In this paper, a system characterization is proposed that describes the relationship between power generators, loads, storage devices and connections among them. The proposed characterization system should be satisfied to guarantee safe operation of a given power flow system by preserving the $SOC$ bounds of storage devices. That is, to have a feasible power flow assignment, there are many issues such as how the power limitations (i.e., maximum and minimum power levels) of power generators and loads must be decided, how large be the capacity of a storage device, and the physical arrangement of connections that must be considered. This paper also shows an optimization problem that consists of optimizing storage capacity, the use of power generators both renewable and non-renewable, and matching with the power demand. Several demonstration scenarios are discussed in this paper for the application and validation of our proposed system characterization.

Effective energy management in microgrids is essential for integrating renewable energy sources and maintaining operational stability. Machine learning (ML) techniques offer significant potential for optimizing microgrid performance. This study provides a comprehensive comparative performance evaluation of four ML-based control strategies: deep Q-networks (DQNs), proximal policy optimization (PPO), Q-learning, and advantage actor–critic (A2C). These strategies were rigorously tested using simulation data from a representative islanded microgrid model, with metrics evaluated across diverse seasonal conditions (autumn, spring, summer, winter). Key performance indicators included overall episodic reward, unmet load, excess generation, energy storage system (ESS) state-of-charge (SoC) imbalance, ESS utilization, and computational runtime. Results from the simulation indicate that the DQN-based agent consistently achieved superior performance across all evaluated seasons, effectively balancing economic rewards, reliability, and battery health while maintaining competitive computational runtimes. Specifically, DQN delivered near-optimal rewards by significantly reducing unmet load, minimizing excess renewable energy curtailment, and virtually eliminating ESS SoC imbalance, thereby prolonging battery life. Although the tabular Q-learning method showed the lowest computational latency, it was constrained by limited adaptability in more complex scenarios. PPO and A2C, while offering robust performance, incurred higher computational costs without additional performance advantages over DQN. This evaluation clearly demonstrates the capability and adaptability of the DQN approach for intelligent and autonomous microgrid management, providing valuable insights into the relative advantages and limitations of various ML strategies in complex energy management scenarios.

The introduction of an energy storage system plays a vital role in the integration of renewable energy by keeping a stable operation and enhancing the flexibility of the power flow system, especially for an islanding microgrid which is not tied to a grid and for a self-contained microgrid which tries to stay independent from a grid as much as possible. To accommodate the effects of power fluctuations of distributed energy resources and power loads on power systems, a power flow assignment under power balance constraint is essential. However, due to power limitations of power devices, the capacity of storage devices, and power flow connections, the power balance may not be achieved. In this paper, we proposed a system characterization which describes the relation among power generators, power loads, power storage devices, and connections that must be satisfied for a system to operate by keeping $SOC$ limitations of power storage devices. When we consider one power generator, one power load, and one power storage device connected at a single node, the generated energy by the generator minus the consumed energy by the load from some start time will increase/decrease the state of charge $\left(SOC\right)$ for the storage device; hence, keeping $SOC$ max/min limitations relies on whether the difference between the generated energy and the consumed energy stays within a certain range or not, which can be computed from the capacity $Ess$ and other parameters. Our contribution in this paper is an extension and generalization of this observation to a system that consists of multiple fluctuating power generators, multiple fluctuating power loads, multiple storage devices, and connections that may not be a full connection between all devices. By carefully enumerating the connection-dependent flow paths of generated energy along the flow direction from generators to storages and loads, and enumerating the connection-dependent flow paths of consumed energy along the counter-flow direction from loads to storages and generators, we have formulated the increase/decrease of $SOCs$ of storage devices caused by the imbalance between generated energy and consumed energy. Finally, considering the max/min limitations of $SOCs$ and fluctuations of power generators and power loads, the conditions that the power generators and the power loads must have for $SOCs$ of storage devices to maintain individual max/min limitations have been derived. The system characterization provides guidelines for a power flow system that can continue safe operation in the presence of power fluctuations. That is, in order for a system to have a feasible power flow assignment, there are the issues of how large the capacity of a power storage device should be, how large/small the maximum/minimum power/demand levels of the power generators and the power loads should be, and how the connection should be configured. Several examples using our system characterization are demonstrated to show the possible applications of our results.