Affiliation:
1. Information & Control Engineering Faculty, Shenyang Jianzhu University, Shenyang 110168, China
Abstract
As one of the key technologies for accelerating the construction of the ubiquitous Internet of Things, demand response (DR) not only guides users to participate in power market operations but also increases the randomness of grid operations and the difficulty of load forecasting. In order to solve the problem of rough feature engineering processing and low prediction accuracy, a short-term load forecasting model of LSTM neural network considering demand response is proposed. First of all, in view of the strong randomness and complexity of input features, the weighted method is used to process multiple input features to strengthen the contribution of effective features and tap the potential value of features. Secondly, an improved genetic algorithm (IGA) is used to obtain the best LSTM parameters; finally, the special gate structure of the LSTM model is used to selectively control the influence of input variables on the model parameters and perform load forecasting. The experimental results show that the research has high prediction accuracy and application value and provides a new way for the development of power load forecasting.
Funder
National Key Research and Development Plan
Subject
Multidisciplinary,General Computer Science
Reference29 articles.
1. SoC-based droop coefficients stability region analysis of the battery for stand-alone supply systems with constant power loads;R. Wang;IEEE Transactions on Power Electronics,2021
2. A hierarchical event detection method based on spectral theory of multidimensional matrix for power system;D. Ma;IEEE Transactions on Systems, Man, and Cybernetics: Systems,2019
3. A Multiagent-Based Consensus Algorithm for Distributed Coordinated Control of Distributed Generators in the Energy Internet
4. Bi-level planning for integrated energy systems incorporating demand response and energy storage under uncertain environments using novel metamodel
5. Regional Energy Internet Construction Framework and Key Tasks
Cited by
9 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献