EV Charging Load Disaggregation for Peak Grid Demand Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing adoption of electrical vehicles is leading to unprecedented peak loads on electrical grids, causing transformer overloads, unplanned outages, and stress on the electrical supply infrastructure.
Innovation Solution
A system and method for disaggregating electrical loads and detecting electric vehicle (EV) charging using edge-based and cloud-based computing devices, including smart electricity meters and central office servers, which utilize machine-learning algorithms and time-window management techniques to accurately identify EV charging events.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If electrical vehicle charging is increased to meet growing demand, then EV adoption and convenience are improved, but transformer overloads and grid stress worsen
Solution Approach 1:
The patent segments the total electrical load into distinct components using machine learning algorithms that analyze voltage, current, and power consumption patterns. By disaggregating the aggregate load signal into individual appliance and EV charging signatures, the system can identify and manage EV-specific demand separately from other loads, enabling targeted responses to EV charging demands without overwhelming the entire grid infrastructure.
Solution Approach 2:
The system performs preliminary detection and identification of EV charging events before they cause critical grid stress. By continuously monitoring and analyzing load patterns in real-time, the system can predict upcoming EV charging demands and enable utility operators to take preventive actions such as load balancing, dispatching distributed energy resources, or implementing demand response programs before transformer overloads occur.
2Measurement precision
If real-time monitoring of all electrical loads is implemented to detect EV charging, then detection accuracy is improved, but system complexity and cost worsen
Solution Approach 1:
The system employs machine learning algorithms that automatically learn and adapt to the unique electrical signatures of EV chargers and other appliances without requiring manual configuration or expert intervention. The algorithms self-train on historical load data, automatically identifying patterns and characteristics that distinguish EV charging from other loads, thereby achieving high detection accuracy while minimizing the need for complex manual setup and maintenance.
Solution Approach 2:
The patent replaces complex mechanical or manual load analysis methods with computational machine learning algorithms. Instead of using intricate hardware-based monitoring systems or manual load disconnection tests, the system uses software-based algorithms that analyze electrical signal patterns to identify EV charging events, significantly reducing hardware complexity while maintaining or improving detection accuracy.
3Speed
If fast charging rates are used to reduce charging time, then charging speed is improved, but peak load and transformer stress worsen
Solution Approach 1:
The system enables periodic or phased EV charging rather than continuous high-power charging. By detecting EV charging events and coordinating with utility operations, the system can schedule charging in periodic intervals or phases that align with periods of lower grid stress, allowing EVs to charge at high rates when capacity is available while distributing the overall load over time to avoid sustained peak demands that would overload transformers.
Data Source
Figure 1
Figure 1A
Figure 2
AI summary
A system and method for disaggregation of customer electrical usage to detect an electrical vehicle (EV) charger from among other electrical devices. An example electricity meter includes a processor, memory device(s), and applications including a model for detecting EV charging. An example model: associates data from a time-series of paired voltage and current measurements with a moving time-window including a plurality of sub-windows having a cumulative duration of the moving time-window; adds a new sub-window having at least one new paired voltage and current measurement to the moving time-window, and deletes an old sub-window, in a continuing manner; determines a value of power, and a value of volt-amps-reactive, for each sub-window within the moving time-window, wherein a stream of paired P and Q values is created; and determines, based on the stream of paired P and Q values, if an EV was charged and estimates the amount of EV charging power or energy.