Muhammad Rizwan Saeed

Efficient customer selection for sustainable demand response in smart grids

Regulating the power consumption to avoid peaks in demand is a common practice. Demand Response(DR) is being used by utility providers to minimize costs or ensure system reliability. Although it has been used extensively there is a shortage of solutions dealing with dynamic DR. Past attempts focus on minimizing the load demand without considering the sustainability of the reduced energy. In this paper an efficient algorithm is presented which solves the problem of dynamic DR scheduling. Data from the USC campus micro grid were used to evaluate the efficiency as well as the robustness of the proposed solution. The targeted energy reduction is achieved with a maximum average approximation error of ≈ 0.7%. Sustainability of the reduced energy is achieved with respect to the optimal available solution providing a maximum average error less than 0.6%. It is also shown that a solution is provided with a low computational cost fulfilling the requirements of dynamic DR.

Semantic Web Technologies for External Corrosion Detection in Smart Oil Fields

The Oil & Gas industry always seeks to prevent loss of containment (LOC). To prevent such incidents, engineers rely on inputs from various asset databases and software tools to make important safety-related assessments and decisions on a daily basis. One cause of LOC in offshore platforms is external corrosion. The state of corroding assets is extensively monitored and recorded through a variety of data collection mechanisms by various processes and people. Due to heterogeneity of these data sources, providing on-demand access to information with an integrated view can be challenging. A unified view of current data sources is desirable for decision making as it could lead to identification of telltale signatures of LOC events. However, manually cross-referencing and analyzing such data sources is labor intensive. Another challenge is knowledge management, which refers to a systematic way to capture the results of various engineering analyses and automated prediction models. It is beneficial to capture this knowledge for two reasons: (i) auditing, archiving, and training purposes, and (ii) mining of LOC signatures and warning signs for developing machine learning prediction techniques. We propose the application of semantic web technologies for a holistic and expressive representation of various heterogeneous data sources at scale to deal with information management issues. The key elements of our approach are a reusable asset integrity monitoring ontology and an external corrosion ontology that model various elements from the domain, and a knowledgebase that can serve as a system of record for observed data as well as new knowledge acquired through inferencing and machine learning analytics. We further describe the methodology followed to populate the knowledgebase and how it can be used to convey assessments and alerts to the right people so that actions are taken to address identified risks. We show that data from multiple sources can be integrated into a central repository serving as a single endpoint for maintaining and retrieving knowledge. We present our integration framework and evaluate the advantages of our approach in terms of expressiveness and ease of information access. Our metadata and knowledge management platform for external corrosion can be highly beneficial for our strategic vision of LOC early prediction and prevention. The expressiveness afforded by the semantic web stack enables rapid integration and facilitates analysis of multiple data sources related to corrosion detection. The end goal for an enterprise is not just storing and managing lots of data, but to get actionable insights fast. Our proposed solution is a stepping stone towards LOC prevention.

Curtailment Estimation Methods for Demand Response: Lessons Learned by Comparing Apples to Oranges

Accurate estimation and evaluation of consumption reduction achieved by participants during Demand Response is critical to Smart Grids. We perform an in-depth study of popular estimation methods used to determine the extent of consumption shedding during DR, using a real-world Smart Grid dataset from the University of Southern California campus microgrid. We provide insights to the process of selecting a reasonable baseline with respect to potential misinterpretation of the estimation of electricity consumption reduction during DR.

Automatic Integration and Querying of Semantic Rich Heterogeneous Data: Laying the Foundations for Semantic Web of Things.

Abstract Enormous amount of data from physical objects, such as devices comprising Internet of Things (IoT), is being made available through Web APIs on a daily basis. Manual discovery and integration of relevant data sources can be cumbersome. A unified view of relevant data sources is desirable for creating applications for monitoring and decision making. Considerable research has been conducted in the Semantic Web domain in terms of modeling and integrating data from physical devices, which has the potential of becoming one of the foundations for the future of IoT. In this chapter, we present different techniques for modeling semantic rich data using ontologies. We highlight the benefits of semantic modeling in terms of ease of data integration. We then discuss approaches of querying semantically rich data using various techniques aimed at users with different levels of expertise. We present this discussion in the context of how the suite of technologies that have been developed for Semantic Web can facilitate in effective handling of IoT infrastructure.

ASQFor: Automatic SPARQL query formulation for the non-expert

The combination of data, semantics, and the Web has led to an ever growing and increasingly complex body of semantic data. Accessing such structured data requires learning formal query languages, such as SPARQL, which poses significant difficulties for nonexpert users. To date, many interfaces for querying Ontologies have been developed. However, such interfaces rely on predefined templates and require expensive customization. Natural Language interfaces are particularly preferable to other interfaces for providing users with access to data, however the inherent difficulty in mapping NLP queries to semantic data is the ambiguity of natural language. To avoid the pitfalls of existing approaches, while at the same time retaining the ability to capture users’ complex information needs, we propose a simple keyword-based search interface to the Semantic Web. Specifically, we propose Automatic SPARQL Query Formulation (ASQFor), a systematic framework to issue semantic queries over RDF repository using simple concept-based search primitives. ASQFor has a very simple interface, requires no user training, and can be easily embedded in any system or used with any semantic repository without prior customization. We demonstrate via extensive experimentation that ASQFor significantly speeds up the construction of query formulation while at the same time matching the precision and recall of hand-crafted optimized queries.