XENDEE Releases New Generative Algorithm to Enable Multi-Year Microgrid Optimization with Industry Leading Accuracy and 12,000% Runtime Reduction
XENDEE Corporation has developed and implemented a new patent pending algorithm capable of reducing the runtime required for multi-year techno-economic optimization of a Microgrid by 12,000% versus existing solutions. This technique allows project planners to optimize Microgrid designs and analyze projected returns far more accurately, while visualizing the changing system dispatch as a response to degradation and strategic reinvestments.
XENDEE's new Adaptive Multi-year Analysis algorithm delivers unrivaled accuracy by considering key changes in the technical and financial environment including: demand growth, updated fuel prices, utility tariffs, actual loan terms, changing technology capital costs, and new carbon taxes, amongst others. Additionally, this adaptive solution reduces runtimes to such an extent, that engineers and even sales professionals are able to run cloud based optimizations and feasibility studies on-site, enabling an entirely new set of business opportunities and rapid client acquisition.
"The key to unlocking more investment in distributed energy is reliable financial projections," said Michael Stadler, Ph.D., CTO of XENDEE. "Governments, corporations and private citizens all over the world recognize the benefits of distributed energy resources, but to reach a critical mass of Microgrid technologies, the value has to be predictable, reliable and financialy viable to investors, lenders and decision makers."
XENDEE's new algorithm looks at the complex problem of analyzing each year of Microgrid development in a novel yet creatively simple way. Unlike competing systems that analyze the entire project timeline in one grand equation, XENDEE creates an adaptive series, moving through each year of the project horizon independently allowing the software to make the right decision at each year of the timeline before updating all the relevant data and moving onto the next year. This solution not only decreases the runtimes of multi-year optimizations by up to 12,000% but also creates a more accurate solution by prioritizing known and current information before making assumptions about the future.
Additionally, the XENDEE platform can make intelligent decisions during each year, such as recommending against a certain technology or suggesting that investment be broken up over the project horizon to take advantage of new policies or developments.
"XENDEE is the only optimization software with a 'real' multi-year optimization framework. This is incredibly important, since reinvestment and degradation can change project financials such as NPV and IRR significantly," said Zack Pecenak, Ph.D., Lead Engineer at XENDEE. "Competing technologies have the ability to consider multiple years, but with limited projection options, its effect is either minimized or unnecessarily magnified and does not examine any reinvestment. Additionally, the run times can be significant enough to dissuade professional use, limiting the accuracy of multimillion dollar investment decisions."
Together with the other stages of XENDEE's end-to-end microgrid design platform, this new multi-year adaptive optimization tool facilitates a quick and efficient design process. Additionally, as a cyber-secure Software as a Service solution, the entire XENDEE platform is designed to keep all relevant data in one streamlined system from initial viability studies to advanced powerflow simulation, as well as facilitate sharing projects securely between teams or forwarding branded financial projections to clients and financiers.
About XENDEE: XENDEE develops Microgrid design automation and decision support software that helps planners and investors validate the technical and financial performance of projects with confidence. The platform enables a broad audience, from business decision makers to scientists, with the objective of supporting investments in Microgrids and DER projects as well as maintaining electric power reliability when integrating sources of renewable generation.
Scaling Use Case
Utilizing Machine Learning to Predict Public Transportation Times
Real-time Insights: A Case Study for the Next Generation of Smart Construction Ecosystem