Electric-Thermal Energy Scheduling Under Voltage and Heat Constraints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electric-thermal integrated energy systems face challenges in ensuring safety due to the randomness and intermittence of renewable energy sources like wind and photovoltaic power, leading to potential voltage violations and insufficient safety studies, while also lacking comprehensive economic optimization.
Innovation Solution
An electric-thermal integrated energy control method using a pretrained SA-PSO-BP neural network to predict renewable energy and multivariate loads, construct an objective function with power and heat network constraints, and optimize scheduling through a simulated annealing-particle swarm optimization algorithm to ensure safe and economical operation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If renewable energy sources (wind and photovoltaic power) are incorporated into integrated energy systems to satisfy energy and environmental protection requirements, then clean energy consumption increases, but the randomness and intermittence of these sources cause voltage violations and safety accidents
Solution Approach 1:
The patent applies preliminary action by using a SA-PSO-BP neural network to predict renewable energy output and load demands before scheduling decisions are made. This advance prediction allows the system to prepare for potential voltage violations and safety issues caused by the randomness and intermittence of wind and photovoltaic power, enabling preventive control measures to be implemented before problems occur.
Solution Approach 2:
The patent implements feedback by constructing an objective function that incorporates safety constraints and using a simulated annealing-particle swarm optimization algorithm to continuously adjust scheduling decisions based on predicted renewable energy output and system state. This closed-loop feedback mechanism ensures voltage violations are prevented while maximizing renewable energy consumption.
2Productivity
If existing electric-thermal integrated energy systems focus on economic optimization and improvement of renewable energy infiltration rate, then economic efficiency improves, but safety studies are insufficient and safety accidents may occur
Solution Approach 1:
The patent merges economic optimization and safety assurance into a unified control framework. The objective function simultaneously incorporates economic costs (electricity purchasing/selling, gas consumption) and safety constraints (voltage limits, system reliability), allowing the system to achieve both high renewable energy infiltration rates and adequate safety levels through coordinated optimization.
Solution Approach 2:
The patent applies parameter changes by using the simulated annealing-particle swarm optimization algorithm to dynamically adjust scheduling parameters (power generation allocation, load distribution, energy storage dispatch) based on predicted renewable energy output. This enables the system to adapt to varying conditions and maintain both economic efficiency and safety across different operating scenarios.
3Measurement precision
If the SA-PSO-BP neural network is used to predict renewable energy and loads, then prediction accuracy improves, but the training process becomes more complex requiring iterative updates of weights and thresholds
Solution Approach 1:
The patent uses the particle swarm optimization algorithm as an intermediary to train the BP neural network. Instead of directly optimizing the complex neural network weights and thresholds, the PSO algorithm serves as a mediator that guides the training process by searching for optimal weight configurations based on prediction accuracy, thereby simplifying the training complexity while maintaining high prediction accuracy.
Data Source
AI summary
An electric-thermal integrated energy control method is provided. The method comprises predicting renewable energy and multivariate loads in an integrated energy system based on a pretrained SA-PSO-BP neural network; constructing an objective function of the integrated energy system, and adding power network constraints and heat network constraints for optimal scheduling; and obtaining an optimal solution of the objective function by means of a SA-PSO algorithm based on prediction results of the renewable energy and the multivariate loads, and controlling the integrated energy system according to the optimal solution of the objective function; wherein, a training process of the SA-PSO-BP neural network comprises: training a BP neural network by means of a feature training set, and iterating and updating weights and thresholds in the BP neural network in the training process by means of the SA-PSO algorithm to obtain the SA-PSO-BP neural network.