Virtual Peaker Plant Scheduling for Microgrid Peak Demand
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Centralized base load power plants struggle to respond timely to rapid changes in power demand, necessitating a new form of peaker power plant that can complement decentralized renewable energy and storage assets to manage peak grid power demand.
Innovation Solution
A virtual peaker power plant (VPPP) is developed using a scheduler model with a neural network that aggregates microgrids, optimizing battery charge/discharge and power generation to minimize peak demand on the electrical grid by predicting demand and pricing, and using gradient descent algorithms and mixed integer non-linear programming to create schedules for battery charge, controllable power generation, and load dispatch.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If centralized base load power plants are replaced by decentralized renewable power generation systems, then environmental sustainability is improved, but the ability to respond timely to rapid changes in power demand deteriorates
Solution Approach 1:
The patent segments the centralized power generation system into multiple decentralized microgrids, each with its own renewable generation and storage assets. This segmentation allows individual microgrids to respond independently and rapidly to local demand changes while collectively providing sustainable power generation across the broader grid.
Solution Approach 2:
The patent implements day-ahead scheduling that pre-coordinates battery charge/discharge cycles and renewable generation schedules across multiple microgrids. This preliminary action ensures that energy storage systems are charged during low-demand periods and discharged during peak demand periods, enabling rapid response to demand changes without requiring actual demand spikes first.
2Productivity
If cloud-based virtual power plants aggregate distributed power generation and energy storage systems, then power generation enhancement is improved, but system complexity increases
Solution Approach 1:
The patent creates a universal virtual peaker power plant platform that can aggregate and coordinate multiple types of distributed energy resources including solar, wind, and battery storage systems across different microgrids. This multi-functional platform handles diverse generation and storage technologies through a single coordinated control architecture, enhancing overall power generation capability while managing system complexity through standardization.
3Loss of time
If a virtual peaker power plant uses neural network models for scheduling, then computational speed is improved, but solution precision may deteriorate compared to optimization algorithms
Solution Approach 1:
The patent uses the neural network model to generate preliminary day-ahead schedules that provide fast initial solutions for battery charge/discharge and renewable generation scheduling. These preliminary schedules are then refined using gradient descent optimization algorithms, combining the speed advantage of neural networks with the precision of mathematical optimization to achieve both rapid computation and accurate results.
Data Source
AI summary
A method and system for a virtual peaker power plant (VPPP) that develops scheduler models for grid interactive power flow between an aggregation of multiple microgrids or stand-alone distributed energy resources (DERs), controlled by the VPPP and a main electrical grid. The VPPP provides day ahead forecasts for grid demand and costs of electrical power determined from external sources. Grid peak prediction software executing in the VPPP develops day ahead forecasts and day ahead schedules for power generation demand, energy storage and load dispatch from the data supplied by multiple microgrids connected to the VPPP. The VPPP generates and downloads a scheduler model for each microgrid to a controller controlling the microgrid. The controller uses the scheduler model to develop schedules and demand forecasts for the microgrid.