Glenn Ellis

Short-term load forecasting using artificial neural networks

The deregulation of the power system industry has made short term load forecasting increasingly important. This paper presents an artificial neural network based hour ahead load forecasting model that improves upon previous models by using the entire load profile of the previous day, rather than making potentially unjustified assumptions about the functional relationship between past hours load and current load. Historical load data for the ISO-New England control area was used to test the proposed model. The mean absolute percentage error for the hour ahead load forecasting was found to be 0.439%, which compares favorably to previous models. In addition, seasonal changes and weekends appear to have relatively small effects on the network performance. This suggests that the use of the 24 past hours load as input variables can potentially create better hour-ahead forecasting models.

New pedagogical approaches in engineering mechanics yield increased student understanding, confidence, and commitment

The Picker Engineering Program at Smith College has formed a close partnership with Smiths Department of Education and Child Study and Department of Educational Outreach in an effort to fundamentally change the delivery of the engineering curriculum. This paper presents learner-centered educational strategies used in Continuum Mechanics I, a course that includes topics from engineering statics, dynamics, and mechanics of materials. Pedagogical elements used in this course include a variety of active learning strategies in the classroom, conceptual frameworks and narratives, project-based learning, metacognitive approaches, and an explicit effort to make a connection with other subjects in the liberal arts. An assessment of these strategies based upon the responses of 27 women who have taken the course is presented and shows that these strategies are effective in positively influencing student learning and attitudes.

Deconstructing Engineering Education Programmes: The DEEP Project to reform the mechanical engineering curriculum

The goal of the Deconstructing Engineering Education Programmes project is to revise the mechanical engineering undergraduate curriculum to make the discipline more able to attract and retain a diverse community of students. The project seeks to reduce and reorder the prerequisite structure linking courses to offer greater flexibility for students. This paper describes the methods used to study the prerequisites and the resulting proposed curriculum revision. The process involved dissecting each course into topics at roughly the level of a line in a syllabus, editing the list of topics, associating prerequisites and successors to each topic and then using a genetic algorithm to produce clusters of topics. The new curriculum, which consists of 12 clusters, each of which could be a full year course, is quite different from the traditional curriculum.

Learning engineering mechanics through video production

This paper presents an approach to integrating student-produced videos into an engineering mechanics class. Each student worked in a production team to produce a two- to three-minute educational video investigating a combined translational/rotational motion. Through this experience students expanded their communication skills by becoming familiar with the technical and creative skills of video production. They also expanded their understanding of mechanics by studying real-world applications and communicating their results. Throughout the project, students received extensive assistance from the colleges media services staff- including workshops on managing and planning production, shooting and editing. Once the videos were completed, students were encouraged to reflect upon their experience through peer reviews and group reflections. Student feedback is presented and supports the success of the activity.

Using knowledge building to support deep learning, collaboration and innovation in engineering education

Knowledge building is a potentially transformative approach to engineering education. In knowledge building students participate in an interactive discourse in which they work together to broaden ideas, reform problems and share knowledge-the result being a deeper level of understanding and the collaborative production of new knowledge. In 2009 we conducted a knowledge building pilot study in the Picker Engineering Program at Smith College. In this study students worked together to formulate a question about the potential for a conscious machine and then engaged in an intensive knowledge building discourse. Assessment data showing the effectiveness of the approach and research questions arising from the study are presented.