Energy supply feedback and meteorology factor thermal load prediction method

Abstract

The invention relates to the multi-energy combined network thermal supply field, and provides a thermal load prediction method that determines energy supply feedback and meteorology factors of thermalsupply demands on the load side; the method comprises the following steps: 1, converting influences on outdoor temperature by a wind speed into a corresponding temperature variation, and calculatingan equivalent outdoor temperature under a zero wind condition; 2, using primary pipe network water return temperature, primary pipe network water return velocity, secondary pipe network water return temperature, secondary pipe network water inlet velocity and primary pipe network water inlet temperature in the history data and the equivalent outdoor temperature as the input, using the primary network water inlet temperature as the output, and training a RBF nerve network; 3, using the trained RBF nerve network to predict the primary network water inlet temperature. A thermal load complex modelis hard to build, and heat transfer lag time-delay cannot form thermal load supply and demand balance; the thermal load prediction method can solve said problems.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to view more

AI Technical Summary

Benefits of technology

This patented technology uses various aspects such as temperatures from previous systems for calculating thermal loads accurately while also taking into account other variables like weather conditions during peak hours when electricity prices were low. By doing this, it allows for more efficient use of resources than traditional methods.

Problems solved by technology

Technological Problem: Current Energy Intelligence Networks (EIN) predict loads accurately only from past history without considering future changes over longer timescales. However, there may still exist issues such as long wait before starting up new equipment or poor performance at peak hours. Additionally, E IN also requires accurate weatheld temperatures during deployment to ensure proper functioning of multiple types of devices like solar panels.

Images