Unit commitment (UC) is a critical component for the power system dispatching departments. Current methodologies for solving UC problems predominantly rely on mixed-integer linear programming and are supplemented by data-driven approaches. These methodologies have two primary limitations: first, as the scale of the power grid expands, the complexity of algorithms increases sharply. Second, they fail to fully exploit grid topology information and historical data trends. To address these limitations, this article proposes a constrained graph-temporal convolutional network, which addresses the UC problem by directly predicting power output with constraints. The algorithm takes historical load data from grid nodes as input, utilizes graph convolutional networks to capture the physical grid topology information, and employs temporal convolutional networks to extract temporal features. Ultimately, the output of the graph-temporal convolutional network is projected into the feasible domain through a linear constraint activation layer, achieving accurate power prediction. Experiments conducted on the IEEE 30-BUS and IEEE 118-BUS systems validate the feasibility and superiority of our method in terms of accuracy and computational efficiency.

Evaluating the performance of database systems is crucial when database vendors or researchers are developing new technologies. But such evaluation tasks rely heavily on actual data and query workloads that are often unavailable to researchers due to privacy restrictions. To overcome this barrier, we propose a framework for the release of a synthetic database which accurately models selected performance properties of the original database. We improve on prior work on synthetic database generation by providing a formal, rigorous guarantee of privacy. Accuracy is achieved by generating synthetic data using a carefully selected set of statistical properties of the original data which balance privacy loss with relevance to the given query workload. An important contribution of our framework is an extension of standard differential privacy to multiple tables.

The effective analysis of social networks and graph-structured data is often limited by the privacy concerns of individuals whose data make up these networks. Differential privacy offers individuals a rigorous and appealing guarantee of privacy. But while differentially private algorithms for computing basic graph properties have been proposed, most graph modeling tasks common in the data mining community cannot yet be carried out privately.

Auditing the changes to a database is critical for identifying malicious behavior, maintaining data quality, and improving system performance. But an accurate audit log is a historical record of the past that can also pose a serious threat to privacy. Policies which limit data retention conflict with the goal of accurate auditing, and data owners have to carefully balance the need for policy compliance with the goal of accurate auditing. In this paper, we provide a framework for auditing the changes to a database system while respecting data retention policies. Our framework includes a historical data model that supports flexible audit queries, along with a language for retention policies that hide individual attribute values or remove entire tuples from history. Under retention policies, the audit history is partially incomplete. We formalize the meaning of audit queries on the protected history, which can include imprecise results. We implement policy application and query answering efficiently in a standard relational system, and characterize (both theoretically and experimentally) the cases where accurate auditing can be achieved under retention restrictions.

Auditing the changes to a database is critical for identifying malicious behavior, maintaining data quality, and improving system performance. But an accurate audit log is a historical record of the past that can also pose a serious threat to privacy. In many domains, retention policies govern how long data can be preserved by an institution. Regulations like FERPA and HIPAA (in the U.S.) or the Directive of Data Protection (in the EU), require strict retention periods to be observed, mandating the disposal of past data. In addition, institutions often adopt their own retention policies, choosing to remove sensitive data after a period of time to avoid its unintended release, or to avoid disclosure that could be forced by subpeona.