Search

With the development of intelligent distribution networks and the proposal of the carbon peaking and carbon neutrality goals, the importance of demand‐side management for the improvement of flexible power operation systems is becoming increasingly prominent. To solve the problems of the excessive peak–valley load differences, the insufficient utilization of demand‐side resources, and the unreasonable pricing of aggregators, this paper proposes a three‐stage economy optimization method for the aggregator based on EV(electric vehicle) user response volumes. To gain the advantages of different types of EVs while increasing the dispatchable capacity, the contract mode between the aggregator and EVs is divided into three categories: complete dispatching, rolling reward and punishment mechanism dispatching, and free dispatching. Based on the cloud model, considering loss aversion, the user's own time flexibility, and the impact of the tariff set by the aggregator on the user's decision‐making, we introduced indicator weights to obtain the improved cloud model. Based on the improved cloud model, a user response volume model is obtained. Then, the aggregator performs a three‐stage pricing optimization operation for EVs based on the bid‐winning peak shaving capacity. In the first stage, the attraction between EVs and charging stations is determined based on the law of gravity, and the charging and discharging reward electricity price is set. In the second stage, the dynamic electricity price of three types of EVs and the charging punishment electricity prices of the rolling reward and punishment mechanism dispatching type are determined. In the third stage, the electricity price of the rolling reward and punishment dispatching EVs is further optimized based on their lack of peak shaving capacity. The method proposed in the paper has been verified to be effective in increasing aggregator profits, increasing EV dispatch capacity, and reducing EV charging costs through the example analysis. [ABSTRACT FROM AUTHOR]

Energy forecasting plays a vital role in mitigating challenges in data rich smart grid (SG) systems involving various applications such as demand‐side management, load shedding, and optimum dispatch. Managing efficient forecasting while ensuring the least possible prediction error is one of the main challenges posed in the grid today, considering the uncertainty in SG data. This paper presents a comprehensive and application‐oriented review of state‐of‐the‐art forecasting methods for SG systems along with recent developments in probabilistic deep learning (PDL). Traditional point forecasting methods including statistical, machine learning (ML), and deep learning (DL) are extensively investigated in terms of their applicability to energy forecasting. In addition, the significance of hybrid and data pre‐processing techniques to support forecasting performance is also studied. A comparative case study using the Victorian electricity consumption in Australia and American electric power (AEP) datasets is conducted to analyze the performance of deterministic and probabilistic forecasting methods. The analysis demonstrates higher efficacy of DL methods with appropriate hyper‐parameter tuning when sample sizes are larger and involve nonlinear patterns. Furthermore, PDL methods are found to achieve at least 60% lower prediction errors in comparison to other benchmark DL methods. However, the execution time increases significantly for PDL methods due to large sample space and a tradeoff between computational performance and forecasting accuracy needs to be maintained. [ABSTRACT FROM AUTHOR]

Non‐intrusive load monitoring (NILM) is an important technology for deeply mining consumers' internal electricity consumption information, which can improve the level of awareness of the load and significantly improve the demand‐side management capability of the smart grid. For a long time, traditional NILM faces the challenge of huge data, long training time and low accuracy. To address this issue, this paper proposes an adaptative lightweight seq2subseq model. The model adaptively determines the optimum window length of the active power segment to extract the appliance characteristics and thus reduces the redundant data to construct the appliance‐level‐seq2subseq model. The proposed model significantly improves the ability to extract and utilize information. At the same time, transfer learning is used to ban the training of appliance models with similar characteristics, further reducing model complexity and training time. The experimental results based on the REDD dataset verify the method's effectiveness. Compared with the seq2seq and seq2point models, the proposed model achieved better accuracy and F1 score, up to 98.10% and 90.29%, respectively. At the same time, the proposed method is further verified on UK‐DALE, which proves that the proposed method has good portability and robustness. [ABSTRACT FROM AUTHOR]