Cost-Aware Text-to-SQL: An Empirical Study of Cloud Compute Costs for LLM-Generated Queries

Text-to-SQL systems powered by Large Language Models (LLMs) achieve high accuracy on standard benchmarks, yet existing efficiency metrics such as the Valid Efficiency Score (VES) measure execution time rather than the consumption-based costs of cloud data warehouses. This paper presents the first systematic evaluation of cloud compute costs for LLM-generated SQL queries. We evaluate six state-of-the-art LLMs across 180 query executions on Google BigQuery using the StackOverflow dataset (230GB), measuring bytes processed, slot utilization, and estimated cost. Our analysis yields three key findings: (1) reasoning models process 44.5% fewer bytes than standard models while maintaining equivalent correctness (96.7%-100%); (2) execution time correlates weakly with query cost (r=0.16), indicating that speed optimization does not imply cost optimization; and (3) models exhibit up to 3.4x cost variance, with standard models producing outliers exceeding 36GB per query. We identify prevalent inefficiency patterns including missing partition filters and unnecessary full-table scans, and provide deployment guidelines for cost-sensitive enterprise environments.

HENRI: High Efficiency Negotiation-based Robust Interface for Multi-party Multi-issue Negotiation over the Internet

This paper proposes a framework for a full fledged negotiation system that allows multi party multi issue negotiation. It focuses on the negotiation protocol to be observed and provides a platform for concurrent and independent negotiation on individual issues using the concept of multi threading. It depicts the architecture of an agent detailing its components. The paper sets forth a hierarchical pattern for the multiple issues concerning every party. The system also provides enhancements such as the time-to-live counters for every advertisement, refinement of utility considering non-functional attributes, prioritization of issues, by assigning weights to issues.

A Survey of Classification Techniques in the Area of Big Data

Big Data concern large-volume, growing data sets that are complex and have multiple autonomous sources. Earlier technologies were not able to handle storage and processing of huge data thus Big Data concept comes into existence. This is a tedious job for users unstructured data. So, there should be some mechanism which classify unstructured data into organized form which helps user to easily access required data. Classification techniques over big transactional database provide required data to the users from large datasets more simple way. There are two main classification techniques, supervised and unsupervised. In this paper we focused on to study of different supervised classification techniques. Further this paper shows a advantages and limitations.

An Alternate Approach for Designing a Domain Specific Image Search Prototype Using Histogram

Everyone knows that thousand of words are represented by a single image. As a result image search has become a very popular mechanism for the Web searchers. Image search means, the search results are produced by the search engine should be a set of images along with their Web page Unified Resource Locator. Now Web searcher can perform two types of image search, they are Text to Image and Image to Image search. In Text to Image search, search query should be a text. Based on the input text data system will generate a set of images along with their Web page URL as an output. On the other hand, in Image to Image search, search query should be an image and based on this image system will generate a set of images along with their Web page URL as an output. According to the current scenarios, Text to Image search mechanism always not returns perfect result. It matches the text data and then displays the corresponding images as an output, which is not always perfect. To resolve this problem, Web researchers have introduced the Image to Image search mechanism. In this paper, we have also proposed an alternate approach of Image to Image search mechanism using Histogram.

A Framework for Semi-automated Web Service Composition in Semantic Web

Number of web services available on Internet and its usage are increasing very fast. In many cases, one service is not enough to complete the business requirement; composition of web services is carried out. Autonomous composition of web services to achieve new functionality is generating considerable attention in semantic web domain. Development time and effort for new applications can be reduced with service composition. Various approaches to carry out automated composition of web services are discussed in literature. Web service composition using ontologies is one of the effective approaches. In this paper we demonstrate how the ontology based composition can be made faster for each customer. We propose a framework to provide precomposed web services to fulfil user requirements. We detail how ontology merging can be used for composition which expedites the whole process. We discuss how framework provides customer specific ontology merging and repository. We also elaborate on how merging of ontologies is carried out.