Synthetic Power Network Modeling for Building-Level Outage Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing power outage prediction methods for natural disasters lack accuracy and require extensive data, especially for the distribution system, which is often confidential and not publicly available, limiting their applicability and precision in estimating power outages at the building level.
Innovation Solution
A method to generate a synthetic power distribution network using publicly available data, such as building and substation locations, assuming power lines follow roads, and classifying them as overhead or underground, to simulate power outages based on fragility functions, providing localized building-level estimates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional statistical models are used for power outage prediction, then model coverage is maintained, but measurement precision and data efficiency deteriorate
Solution Approach 1:
The patent creates a synthetic power distribution network that replicates the topological and spatial characteristics of the actual confidential network. By copying the network structure, connectivity patterns, and geographic distribution of substations and customers, the system achieves accurate power outage predictions without requiring access to the real proprietary data, thus improving measurement precision while reducing data requirements.
Solution Approach 2:
The synthetic network serves as an intermediary between the available public data and the prediction model. Instead of directly using confidential distribution system data, the patent creates this intermediate representation that captures essential network characteristics, enabling accurate predictions while working only with publicly available information.
2Measurement precision
If confidential distribution system data is used, then measurement precision improves, but ease of operation deteriorates
Solution Approach 1:
The patent creates a synthetic power distribution network that replicates the topological and spatial characteristics of the actual confidential network. By copying the network structure, connectivity patterns, and geographic distribution of substations and customers, the system achieves accurate power outage predictions without requiring access to the real proprietary data, thus improving measurement precision while reducing data requirements.
3Ease of operation
If aggregate-level predictions are made, then ease of operation improves, but measurement precision deteriorates
Solution Approach 1:
The patent segments the power distribution network into individual customer-level units within the synthetic network. Each customer node can be independently analyzed for outage probability, enabling building-level predictions. This segmentation allows the model to maintain ease of operation through modular processing while achieving high measurement precision at the individual building level.
Data Source
AI summary
The following relates generally to calculating estimated power outages during a natural disaster event. In this regard, some embodiments create a synthetic network of a power infrastructure of a geographic area by: determining a location of a power substation; determining a location of a customer; determining a location of a power line linking the power substation to the customer; and determining if the power line is overhead or underground. Some embodiments then use the created synthetic network to simulate an event to calculate the estimated power outages during the event.