A Prosumer Power Prediction Method Based on Dynamic Segmented Curve Matching and Trend Feature Perception

Abstract

With the massive installation of distributed renewable energy (DRE) generation, many prosumers with the dual attributes of load and power supply have emerged. Different DRE permeability and the corresponding peak-valley timing characteristics have an impact on the power features of prosumers, so new models and methods are needed to reflect the new features brought about by these factors. This paper proposes a method for predicting the power of prosumers. In this method, dynamic segmented curve matching is applied to reduce the complexity of source–load coupling features and improve the effectiveness of the input features, and trend feature perception based on a temporal convolutional network (TCN) was applied to grasp the power trend of prosumers by predicting the multisegment trend indexes. The LST-Atten prediction model based on a temporal attention mechanism (TAM) and a long short-term memory (LSTM) network was applied to predict “day-ahead” power, which combines the trend indexes and similar curve sets as the input. Simulation results show that the proposed model has higher accuracy than individual models. Furthermore, the proposed model can maintain prediction stability under different renewable energy permeability scenarios.

Reform of Electrical Engineering Undergraduate Teaching and the Curriculum System in the Context of the Energy Internet

“…For example, smart substations based on IoT technology are networked with sensors throughout to achieve the intelligent sensing and comprehensive online monitoring of substations, ensuring that the operation of equipment can be verified remotely [77]. In addition, fault identification and substation IoT convergence, security access, and other technologies provide more kinds of power equipment that is compatible with the stability of operation, leading to reliable support [78]. A large amount of terminal equipment used at the same time as network information transmission brings a greater challenge; if the transmission process cannot guarantee the security of the data and personal privacy, this will lead to serious trust issues.…”

Design and Implementation of Device-level Load Dynamic Adjustment System for Electric Vehicles

“…Similar days can filter historical data with more similar characteristics as the input of the neural network so that the neural network can iterate faster and improve accuracy. As a network model with ultra-long memory Result capacity for time series, TCN is more suitable for the electric vehicle charging load prediction scenario with higher uncertainty and volatility [14][15][16].…”