Search

The state-of-the-art centralized computing framework applied to the optimal market dispatch of energy storage systems (ESS) aggregates data from local ESS units for training on the cloud server due to the limited computing resources on edge. However, this approach poses several challenges, including the lack of joint optimization for multiple ESS units, susceptibility to single point of failure and attacks, and inadequate data privacy protection for ESS owners. This study proposes an adaptive personalized federated reinforcement learning (FRL) for multiple-ESS optimal dispatch in various electricity markets with electric vehicle and renewable energy, achieving both the joint optimization of multiple ESSs and avoiding the degraded performance of FRL's local model. Under an adaptively ESS-related differential privacy protection, local devices and the cloud server are specialized to form multiagent deep reinforcement learning (DRL) model for bidding energy, regulation, and third-party services and update the global models, respectively. Given the adaptability of personalization layer to different agents and clients, an adaptive personalization method is developed by calculating the number of personalization layers with the relative loss of each agent and client in the iteration process. The case study shows that the adaptive personalized FRL outperforms conventional FRL, DRL and optimization algorithms. [Display omitted] • FRL-based algorithm for multiple-ESS optimal market dispatch. • Multiagent DRL model for bidding energy, regulation, and third-party services. • Adaptive personalization layers with the relative loss of each agent and client. • Adaptively ESS-related differential privacy method. [ABSTRACT FROM AUTHOR]

The global resurgence of hydrogen as a clean energy source, particularly green hydrogen derived from renewable energy, is pivotal for achieving a carbon-neutral future. However, scalability poses a significant challenge. This research proposes innovative business models leveraging the low-emission property of green hydrogen to reduce its financial costs, thereby fostering its widespread adoption. Key components of the business workflow are elaborated, mathematical formulations of market parameters are derived, and case studies are presented to demonstrate the feasibility and efficiency of these models. Results demonstrate that the substantial costs associated with the current hydrogen industry can be effectively subsidized via the implementation of proposed business models. When the carbon emission price falls within the range of approximately 86–105 USD/ton, free access to hydrogen becomes a viable option for end-users. This highlights the significance and promising potential of the proposed business models within the green hydrogen credit framework. • Business models for trading green hydrogen credits are designed the first time. • It provides innovative financial solutions to decrease the cost of green hydrogen. • Incentives of utilizing green hydrogen are created using proposed business models. • The adoption of proposed trading framework can stimulate global hydrogen economy. • This work accelerates the progress towards a carbon-neutral future. [ABSTRACT FROM AUTHOR]

The leading-edge technology of Digital Twin (DT) presents potential solutions for challenges associated with renewable energy resources (RER), particularly solar energy, such as optimal management, random nature and unpredictability, maintenance, security, and energy efficiency. These issues are more elevated today due to the widespread adoption of solar energy in the power system. A DT leverages advanced technologies including the Internet of Things (IoT), artificial intelligence, and computing techniques, to observe and confirm the state of physical entities, analyze data and derive valid information to monitor and optimize the entity's operation. This Perspective strives to trace the growing body of advances in the field and proposes opportunity areas for DT of RER (RERDT) and DT of solar energy (DTSE) in various application domains including forecasting, reliability analysis, security, and resiliency. Barriers that hinder the adoption of RERDT and DTSE technologies to meet its continuous operation are discussed, and also possible views as future trends to deal with the challenges are presented. RERDT and DTSE technologies promise to be transformative in enabling flexible and sustainable energy sources as well as in active real-time management since it provides a full comprehension of the resources. [ABSTRACT FROM AUTHOR]

• A novel T-DAD model is proposed for typhoon disaster scenario. • Besides line hardening, we incorporate DG UC into T-DAD's 1st level. • UC and reconfiguration strategies are extended to 24 h instead of load peak periods. • We simulate typhoon "Mangkhut" (2018) with considering more resilience elements. Extreme natural disasters such as typhoon often cause failures in distribution networks within a short time, and even lead to large area blackouts. We propose a tri-level robust optimization framework that combines pre-disaster, in-disaster and post-disaster strategy comprehensively to enhance distribution network resilience. The typhoons are regarded as attackers, and a tri-level Defender-Attacker-Defender model for typhoon disaster is used to integrate multiple resilience resources. In the first level, line hardening and distributed generation unit commitment are used to improve resilience in pre-disaster. The second level contains attack budget, attack time, hardening budget, repair time and load loss. It couples with the third level iteratively to generate the worst failure scenario under typhoon. In the third level, the Nested Column-and-Constraint Generation algorithm is used to solve distribution network reconfiguration and intentional islanding. Simulation time is spanned to the entire 24-hour disaster day. In the end, the proposed framework is tested through a case study using real data from super typhoon "Mangkhut" (2018) in Yangjiang, China. The result shows that it can effectively reduce load loss under the worst typhoon scenario and enhance distribution network resilience with limited resources. [ABSTRACT FROM AUTHOR]

The low-carbon economic operation of integrated energy systems (IES) cannot be separated from the carbon trading and green certificate trading market. Therefore, a low-carbon market mechanism and optimization method for IES is proposed. First, we establish a "green-carbon" offset mechanism to realize the conversion from tradable green certificate (TGC) to carbon quotas to offset system's carbon emissions. Second, considering the impact of market incentives and users' consumption behavior on IES, an energy management method of IES is put forward based on Stackelberg game. IES operators as leaders decide energy prices and trading strategies of carbon, TGC and multi-energy. Energy users as followers participate in the integrated demand response based on energy price. The game is solved by an improved adaptive catastrophic genetic algorithm and CPLEX solver. Finally, we take an industrial park in China as an example to analyze. The results show that the proposed method can significantly reduce the system's carbon emissions while improving the benefits for both IES and consumers. • A mechanism is proposed to offset system carbon emissions with green certificates. • An intelligent pricing and optimal method is proposed based on Stackelberg game. • Carbon capture and power-to-gas technology are used to reduce carbon emissions. • Key parameters sensitivity of the offset mechanism is analyzed for specific cases. [ABSTRACT FROM AUTHOR]

Deploying energy-efficient appliances is one of the most effective ways to save energy bills for residents. However, the existing recommender systems for energy-efficient appliances passively rely on energy consumption patterns without the knowledge of users' true needs. This paper proposes a user-centric energy-efficient appliance personalized recommender system (EEA-PRS) based on information collected from load monitoring platforms and e-commerce websites. The proposed system is built in a novel multi-task learning approach to collaboratively infer user's preference on: (1) common types of appliances that appear in historical data; (2) energy-efficient models of common appliances; and (3) types of appliances that are novel to the users. The proposed system provides supervisory recommendation services with user feedback preferences on appliances as data labeling, which enables closed-loop evaluation to adhere to users' needs and interests. Simulation studies with comparative analysis have been conducted to validate its leading recommendation performance in terms of conforming to user preferences. [ABSTRACT FROM AUTHOR]

Real-time industrial carbon emission estimation aims to estimate emissions more accurately to promote carbon reduction and mitigate climate change. Compared with input-output-based (IOA) analysis methods, the process-based analysis (PA) methods provide more specific information to decision-makers based on extensive detailed data. However, the required data is hard to obtain and normally contains missing data. To address these challenges, this paper proposes a novel deep learning-based carbon emission estimation framework to track the emissions of industrial customers in smart grids with smart meter data. The proposed framework encompasses three pivotal stages: data imputation, device recognition, and emission estimation—collectively referred to as DI-DR-EE. Specifically, the Data Imputation Network (DINet) based on super-resolution perception (SRP) is first introduced to recover the missing smart meter data. Then the recovered data is used to recognize the device states through the Device Recognition Network (DRNet), which thrives upon subspace blueprint separable convolutions (BSConv-S) to elevate the accuracy of device recognition with low-frequency data, all the while optimizing computational efficiency. Finally, the direct emission estimation is conducted based on the device states, and the indirect emission is estimated based on the power consumption. Case studies with five factories connected to the IEEE 57-bus system have verified the effectiveness of the proposed framework. The model training process was executed using Python with PyTorch version 1.8.1, coupled with Cuda 11.1 for accelerated computations. Results underscore that DINet and DRNet outperform established benchmarks, while DI-DR-EE remarkably maintains its capacity to attain estimations within a 10% margin of error, even when grappling with up to 90% missing meter data. • A novel deep learning-based carbon emission estimation framework is proposed to track the emissions of industrial customers. • A Data Imputation Network (DINet) is introduced to reconstruct missing data more efficiently. • A Device Recognition Network (DRNet) is proposed to identify the device states more accurately. • Real-time emission estimation is realized even with incomplete and low-frequency smart meter data. [ABSTRACT FROM AUTHOR]

Most existing data-driven power system short-term voltage stability assessment (STVSA) approaches presume class-balanced input data. However, in practical applications, the occurrence of short-term voltage instability following a disturbance is minimal, leading to a significant class imbalance problem and a consequent decline in classifier performance. This work proposes a Transformer-based STVSA method to address this challenge. By utilizing the basic Transformer architecture, a stability assessment Transformer (StaaT) is developed as a classification model to reflect the correlation between the operational states of the system and the resulting stability outcomes. To combat the negative impact of imbalanced datasets, this work employs a conditional Wasserstein generative adversarial network with gradient penalty (CWGAN-GP) for synthetic data generation, aiding in the creation of a balanced, representative training set for the classifier. Semi-supervised clustering learning is implemented to enhance clustering quality, addressing the lack of a unified quantitative criterion for short-term voltage stability. Numerical tests on the IEEE 39-bus test system extensively demonstrate that the proposed method exhibits robust performance under class imbalances up to 100:1 and noisy environments, and maintains consistent effectiveness even with an increased penetration of renewable energy. Comparative results reveal that the CWGAN-GP generates more balanced datasets than traditional oversampling methods and that the StaaT outperforms other deep learning algorithms. This study presents a compelling solution for real-world STVSA applications that often face class imbalance and data noise challenges. [Display omitted] • The class imbalance issue is addressed using balanced samples generated by CWGAN-GP. • StaaT with multi-head self-attention mechanisms learns important features. • SFCM labels samples undeterminable directly by domain knowledge. • StaaT exceeds other methods, showing robustness amid class imbalances and noises. [ABSTRACT FROM AUTHOR]