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]

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]