Having completed the implementation and roll-out, we are now working with teams in individual markets to build trust and increase forecast adoption. This is where the expertise of the HQ Demand Planners is coming into play. Each month, the team is reviewing, analyzing and sharing forecasts with the markets. At this point, we see the limitations of what the tool can do. The forecasting tool is perfect to find models that minimize forecast error but several proposed models have been found to be unusable and unrealistic.
Demand management solutions have improved on many fronts. One area where some solutions have made particular progress is in the area of providing highly flexible solutions that can evolve as the company's business changes. Demand management solutions need to be flexible! Over time, companies often go on a journey where their forecast accuracy is improved by using more and more data and by forecasting at a more granular levels (For more on this topic, see this article which describes stages in demand forecasting maturity). To support this journey demand management solutions need to be flexible.
Another problem is that the more granular the forecast – SKU at store level by week, for example – the higher the forecast error tends to be. "For sure, the greater degree of error in the store-level forecast, the greater the impact on the lost sale calculation," Fenwick said. "However, even if we hit a 70% accuracy measure, we're still capturing 70% of the potential lost demand in the store due to stock outs. Which, from a forecasting perspective, is a lot better than capturing zero lost demand. As the saying goes, 'if you only forecast to sales, you'll only ever stock to … what you sold.'"
Though distribution system operators have been adding more sensors to their networks, they still often lack an accurate real-time picture of the behavior of distributed energy resources such as demand responsive electric loads and residential solar generation. Such information could improve system reliability, economic efficiency, and environmental impact. Rather than installing additional, costly sensing and communication infrastructure to obtain additional real-time information, it may be possible to use existing sensing capabilities and leverage knowledge about the system to reduce the need for new infrastructure. In this paper, we disaggregate a distribution feeder's demand measurements into: 1) the demand of a population of air conditioners, and 2) the demand of the remaining loads connected to the feeder. We use an online learning algorithm, Dynamic Fixed Share (DFS), that uses the real-time distribution feeder measurements as well as models generated from historical building- and device-level data. We develop two implementations of the algorithm and conduct case studies using real demand data from households and commercial buildings to investigate the effectiveness of the algorithm. The case studies demonstrate that DFS can effectively perform online disaggregation and the choice and construction of models included in the algorithm affects its accuracy, which is comparable to that of a set of Kalman filters.
Machine learning takes artificial intelligence (AI) to the next level by allowing a system to learn without prior programming. Now, restaurants are starting to benefit from this technology. Simon Bocca, COO at Fourth, shared how his company is using machine learning. Fourth recently announced its end-to-end restaurant and hospitality platform and services. The company provides an all-in-one solution for purchase-to-pay, inventory and workforce management with advanced demand forecasting, predictive analytics and collaboration tools.