Abstract
Current intelligent information systems require complex database approaches managing and monitoring data in a spatio-temporal manner. Many times, the core of the temporal system element is created on the relational platform. In this paper, a summary of the temporal architectures with regards to the granularity level is proposed. Object, attribute, and synchronization group perspectives are discussed. An extension of the group temporal architecture shifting the processing in the spatio-temporal level synchronization is proposed. A data reflection model is proposed to cover the transaction integrity with reflection to the data model evolving over time. It is supervised by our own Extended Temporal Log Ahead Rule, evaluating not only collisions themselves, but the data model is reflected, as well. The main emphasis is on the data retrieval process and indexing with regards to the non-reliable data. Undefined value categorization supervised by the NULL_representation data dictionary object and memory pointer layer is provided. Therefore, undefined (NULL) values can be part of the index structure. The definition and selection of the technology of the master index is proposed and discussed. It allows the index to be used as a way to identify blocks with relevant data, which is of practical importance in temporal systems where data fragmentation often occurs. The last part deals with the syntax of the Select statement extension covering temporal environment with regards on the conventional syntax reflection. Event_definition, spatial_positions, model_reflection, consistency_model, epsilon_definition, monitored_data_set, type_of_granularity, and NULL_category clauses are introduced. Impact on the performance of the data manipulation operations is evaluated in the performance section highlighting temporal architectures, Insert, Update and Select statements forming core performance characteristics.
Highlights
1 shows theoftransaction logging in terms of must reflect the data as they existed at the start of the processing, either statement itself or online redo logs are defined by the groups, in which individual files the whole transaction based on the isolation level
The task of conventional databases is to process currently valid data, when changing them, the Update command is physically executed, after executing the Delete command, the relevant records are deleted from the database, and information about their existence is lost from the main structure, even though this information is partially available in backups and log files
The core element influencing the quality and usability of any information system is associated with the data, their correctness, reliability, and accessibility in an effective manner
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. The current state is obtained, followed by the transaction log analysis to get the undo image of the defined timepoint or system change identifier respectively. State of the art is discussed, highlighting the performance limitations, followed by introducing our own proposed improvements or new architecture. Contribution of the section is covered by the data reflection model, by which the transaction reflects multiple data models, which evolve over time in the temporality sphere. Proposed architecture deals with the Index module, Management handler, and Data change module located in the instance memory. The Epsilon_definition can limit the result set by removing non-relevant data changes or changes, which do not reflect defined importance, respectively.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have