About Prompt
- Prompt Type – Dynamic
- Prompt Platform – ChatGPT, Grok, Deepseek, Gemini, Copilot, Midjourney, Meta AI and more
- Niche – Load Forecasting
- Language – English
- Category – Energy Forecasting
- Prompt Title – AI Prompt for Forecasting Electricity Demand in Urban Areas
Prompt Details
**Prompt Type:** Dynamic
**Purpose:** Energy Forecasting – Load Forecasting
**Target Audience:** All AI Platforms
**Description:** This prompt aims to generate accurate and granular electricity demand forecasts for urban areas, incorporating a variety of dynamic factors that influence consumption patterns. It is designed to be adaptable across different AI platforms and datasets, allowing users to customize the specific inputs and output format.
**Prompt Structure:**
“`
Forecast electricity demand for [Target Urban Area] over the [Forecast Horizon], considering the following factors:
**1. Temporal Information:**
* **Start Date:** [YYYY-MM-DD]
* **End Date:** [YYYY-MM-DD]
* **Forecast Resolution:** [Hourly/Daily/Weekly] (Specify desired granularity)
* **Historical Data Period:** [Number] [Years/Months/Weeks/Days] (Specify the length of historical data used for training)
* **Special Days/Periods:** List any known special days or periods within the forecast horizon that may significantly impact demand (e.g., holidays, special events, school breaks). Include the date and a brief description of the event.
**2. Spatial Information:**
* **Geographic Boundaries:** Provide a precise definition of the target urban area. This can include specific geographic coordinates, administrative boundaries (e.g., city limits, zip codes), or a combination of both. If available, provide a shapefile or GeoJSON file defining the area.
* **Spatial Resolution:** If applicable, specify the desired spatial resolution of the forecast (e.g., neighborhood level, grid cell).
**3. Weather Data:**
* **Data Source:** Specify the source of weather data to be used (e.g., a specific weather API, a local weather station, a pre-existing dataset).
* **Variables:** Include relevant weather variables such as temperature, humidity, wind speed, precipitation, cloud cover, and solar irradiance.
* **Data Format:** Specify the format of the weather data (e.g., CSV, JSON). If using an API, provide the necessary API keys or authentication details.
**4. Socioeconomic Factors:**
* **Population Density:** Provide data on population density within the target urban area. This can be overall density or at a finer spatial resolution if available.
* **Economic Activity Indicators:** Include relevant indicators of economic activity such as employment rates, GDP growth, or industrial production indices.
* **Demographic Data:** If available, provide data on demographics like age distribution, household size, and income levels.
**5. External Factors:**
* **Electricity Prices:** Include historical and/or forecasted electricity prices for the target area.
* **Grid Conditions:** If available, provide information on grid conditions such as planned outages, transmission capacity, and renewable energy generation.
**6. Output Format:**
* Specify the desired format for the forecast output (e.g., CSV, JSON, tabular data). Include the specific data fields required, such as date/time, forecasted demand (in kW or MW), and a measure of uncertainty (e.g., confidence interval, standard deviation).
**7. Model Considerations:**
* **Model Type (Optional):** While not strictly required, you can suggest a specific type of forecasting model (e.g., ARIMA, LSTM, Prophet) if deemed appropriate for the task.
* **Evaluation Metrics:** Specify the metrics to be used for evaluating the accuracy of the forecast (e.g., Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE)).
**Example:**
Forecast electricity demand for the city of London, UK over the next 7 days (2024-01-20 to 2024-01-26) at an hourly resolution. Use historical data from the past 3 years. Consider weather data from the OpenWeatherMap API (API key: [YOUR_API_KEY]), population density data from the UK Office for National Statistics, and historical electricity prices from [Data Source]. The output should be in CSV format, including the date/time, forecasted demand (in MW), and a 95% confidence interval. Evaluate the forecast using MAPE and RMSE.
**Note:** Replace the bracketed placeholders with the appropriate values. Be as specific and detailed as possible to ensure the AI model understands the requirements and generates accurate forecasts. This dynamic prompt structure allows for flexibility and customization based on the specific forecasting needs and available data.
“`