SBIR-STTR Award

Training power-grid operators for public utilities has proven difficult. Many trainees fail to learn quickly enough to graduate from Operator training. Despite relatively high salaries, many trainees who graduate are relatively quickly hired away from public utilities by better-paying jobs in the private sector. Public utilities need a better training pipeline for Load Operators. To develop a better training pipeline, InnoSys is applying simulation-based Learning-by-Doing training to Load Operators. This approach efficiently trains people who must understand complex systems in order to resolve faults with unexpected symptoms arising from never-before-experienced situations. Learning by doing exploits the advantages of training within a simulation in a variety of ways. First, training is conducted within the situation in which the knowledge is used—trainees not only learn how the system works, but when specific types of knowledge should be applied. Second, training requires trainees to practice thinking how to solve problems within a context that is similar to their job. If they need help to solve the problem, rather than being told the resolution, they are given hints and use them to resolve the situation—trainees construct their knowledge as they resolve problems. Third, training is constructed to minimize cognitive overload as trainees solve problems--for example, first trainees focus on solving the problem; then they focus on lessons learned. In Phase I, we will first refine methods to capture expertise from experienced, trusted Operators. This will form the basis of the training. Second, we will construct a prototype Learn-by-Doing environment. Experts, trainees, and DOE staff can observe how this training will help learners. Third, as users interact with the prototype, we will obtain feedback on training effectiveness. Commercialization success of our Experiential Load Operation Trainer will require that decision makers who select training must pay attention to (1) the metrics that show the advantages of Learning by Doing, (2) inspecting the instruction and appreciating its advantages, and/or (3) testimonials from students who have experienced Learning by Doing and experts who have observed how effectively it trains. Currently, the market size for operator training via simulation is slightly over $11B. The CAGR for the next 4 years is projected to be about 12.5%. The market size for simulator training for operators will approach $20B. Our commercialization approach is to license our technology and courses to companies that already sell training to power-grid training companies.

Statement of the problem or situation that is being addressed throughout Phase I portion of your proposal: Training power-grid operators for public utilities has proven difficult. Many trainees fail to learn quickly enough to graduate from Operator training. Despite relatively high salaries, many trainees who graduate are relatively quickly hired away from public utilities by better-paying jobs in the private sector. Public utilities need a better training pipeline for Load Operators General statement of how this problem is being addressed: To develop a better training pipeline, InnoSys is applying simulation-based Learning-by-Doing training to Load Operators. This approach efficiently trains people who must understand complex systems in order to resolve faults with unexpected symptoms arising from never-before-experienced situations. Learning by doing exploits the advantages of training within a simulation in a variety of ways. First, training is conducted within the situation in which the knowledge is used—trainees not only learn how the system works, but when specific types of knowledge should be applied. Second, training requires trainees to practice thinking how to solve problems within a context that is similar to their job. If they need help to solve the problem, rather than being told the resolution, they are given hints and use them to resolve the situation—trainees construct their knowledge as they resolve problems. Third, training is constructed to minimize cognitive overload as trainees solve problems--for example, first trainees focus on solving the problem; then they focus on lessons learned. What was done in Phase I: In Phase I, we identified an existing, commercially proven simulation of the power grid to enhance with our training enhancements. We tested and refined methods to capture expertise from experienced, and improve trusted Operators. The expertise was used to design an assessment system which yielded a score of overall performance and identified performance weaknesses. The expertise was also used to design instructional interactions to improve trainee performance and knowledge. What is planned for the Phase II project: We will apply Learning by Doing by creating scenario- based training for (1) load operators facing power outages after natural disaster and (2) unemployed workers who are considering changing careers to become load operators. Both of these training packages will be developed and deployed with refinement from collaborating utilities, tested for effectiveness, and then made commercially available. Commercial Applications and Other

Benefits:
Commercialization success of our Experiential Load Operation Trainer will require that decision makers who select training must pay attention to (1) the metrics that show the advantages of Learning by Doing, (2) inspecting the instruction and appreciating its advantages, and/or (3) testimonials from students and experts who have observed how effectively it trains. Our commercialization approach is to license our technology and courses to companies that already sell training to power-grid training companies. The training methods developed and tested can be applied much more broadly within the power industry and more broadly to utilities and manufacturing industry sectors. Currently, the market size for operator training via simulation is slightly over $11B. The CAGR for the next 4 years is projected to be about 12.5%. The market size for simulator training for operators will approach $20B.