Context-redefined language synthesis for energy consumption prediction using data from mixed remote sensors types

摘要

This paper deals with the design and application issues of context-redefined computer languages for new information technologies. The discussion touches upon these languages implementation problems for intelligent learning agents (ILA), applied for solving the behavior prediction tasks for resource consumption in communal services. The article deals with the second problem in particular. The approach consists in the application of context-redefined language and its support system for problem solution. We focus on principal unpredicted changing of source function algorithms. Built-in context-redefined computer language is an essential tool for this kind of algorithm support. The main part of the intelligent learning agent is performance element. The performance element operates according to the current algorithm, which is described by means of built-in context-redefined language. The main idea of built-in language synthesis is to use main parts of the algorithm for ILA components with proper modification by means another algorithms and context connection. Due to this connection, the original algorithm can be changed directly or indirectly in the process of ILA functioning. We have to extract changing parts of component algorithms and organize proper interaction between every part and the context, which can be changed directly or indirectly. Required adaptive algorithm variation takes place on the base of obtained knowledge. At the same time, the algorithm must be implemented quickly, and the language must be simple and clear. The algorithm efficiency is based on flexibility and modifiability of the language. General constructions of the built-in context-redefined language have been demonstrated with proper comments.