Load Flexibility Forecasting via MINLP Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The electric power grid faces inefficiencies and insecurity due to limited energy storage and reliance on weather-dependent clean energy sources, which are intermittent, making it difficult to integrate distributed resources effectively, and current load forecasting methods lack the accuracy and speed needed to manage rapidly changing power demands.
Innovation Solution
A system and method for forecasting load flexibility using polynomial-time mixed-integer non-linear programming (MINLP) optimization, which receives temperature values from various loads on the power grid to predict flexibility and output information for real-time display, allowing for fine-grained, fast, and accurate load forecasting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If load forecasting is performed at macro level using traditional methods, then computational complexity is reduced, but forecasting accuracy and granularity are insufficient for managing distributed resources
Solution Approach 1:
The patent segments the power system into individual load entities, performing forecasting at the load-by-load basis rather than aggregated macro level. This enables fine-grained flexibility assessment for each load while maintaining computational tractability through modular processing of temperature values and flexibility parameters across multiple loads.
Solution Approach 2:
The patent transforms the forecasting approach by changing from traditional macro-level aggregate parameters to fine-grained load-level parameters including temperature values, temperature set points, and flexibility metrics. This parameter transformation enables more precise forecasting while using polynomial-time MINLP optimization to manage computational complexity.
2Productivity
If traditional load forecasting methods are used, then computational resources are conserved, but forecasting speed is too slow to accommodate rapidly changing power system variables
Solution Approach 1:
The patent performs load flexibility forecasting in advance to generate day-ahead predictions that inform real-time operational decisions. By pre-calculating flexibility parameters and temperature trajectories, the system enables rapid response to changing conditions without requiring intensive real-time computation, thus improving forecasting speed while managing computational resource usage.
3Adaptability or versatility
If weather-dependent clean energy sources are integrated into the power grid, then renewable energy utilization increases, but system intermittency and reliability challenges worsen
Solution Approach 1:
The patent implements a feedback mechanism where load flexibility forecasts inform power generation and dispatch decisions. By predicting available flexibility from distributed loads based on temperature values and comfort constraints, the system provides real-time feedback that enables grid operators to balance intermittent renewable generation with flexible demand, thus maintaining reliability while increasing renewable energy utilization.
Data Source
AI summary
The example embodiments are directed to a system and method for forecasting load flexibility of a power grid. In one example, the method includes receiving temperature values associated with temperature set points of a plurality of loads that are included on a power grid, forecasting a flexibility of the plurality of loads using a polynomial-time mixed-integer non-linear programming (MINLP) optimization based on the received temperature values for the plurality of loads, and outputting information about the forecasted flexibility for display to a display device. The MINLP optimization performs the forecasting of the load flexibility on a fine-grained basis in comparison to conventional methods and is still fast enough that it can be computed in real-time.