| AI & machine learning


to maximize power output. HYDROGRID Insight supports this short-term optimization, which can lead to a 5-10% increase in power output, given typical turbine efficiency patterns. The second pathway is specific to flexible power plants


with storage capabilities. Here, the key to increasing power output is avoiding unnecessary water spillage. We need to manage the water level in reservoirs intelligently and proactively. This means shifting from a reactive approach (e.g., “It’s raining, let’s increase power output”) to a pre-emptive one (e.g., “It’s going to rain tomorrow, let’s drain the reservoir today to catch all that water for later use”). This approach not only benefits power generation but also enhances safety aspects. Interestingly, these strategies align the interests of power producers, the environment, and consumers. By implementing intelligent production planning and water management, we increase the revenue of power generators, make operations safer, support grid stability, and provide power when it’s most needed by consumers. It’s a rare case where interests are perfectly aligned across all parties.


Some practical examples illustrate these benefits:: In India, we helped a hydro operator safely manage their hydropower plant during monsoon season. The plant is located upstream from a large city, and any spillage from the dam could damage the surrounding area. Our intelligent production planning not only improved efficiency and revenue but also increased safety for the local population. In the UK, we assisted the country’s largest hydro producer in optimizing their maintenance planning. We integrated data from multiple systems into a single source of truth, allowing the entire organization - from control room operators to maintenance personnel - to access unified information. This optimization minimized downtime and revenue loss while supporting grid stability by scheduling maintenance during low-demand periods. In Norway, we supported a mid-sized utility with managing water in their complex cascade system. Previously, their shift team needed to be on call 24/7, often waking up at night to manually intervene when water levels were too high or low. By automating much of this intervention management with HYDROGRID Insight, we reduced the number of nighttime wake- ups by about 95%, making it the exception rather than the norm. This greatly benefited the shift team, allowing them to be more refreshed and energized for daytime decision-making.


These examples demonstrate how our solutions can have a significant impact, especially for companies managing complex, multi-plant systems.


Your platform offers real-time optimization. How does machine learning enable this, and what benefits does it bring to hydropower? In the past, planning hydropower generation was relatively straightforward. Ten or twenty years ago, you could create an annual plan for a hydropower plant with only minor adjustments needed throughout the year. For run-of-river plants, the strategy was simple: generate when there’s abundant water. For storage or pumped storage plants, the pattern was predictable: run during the day, pump at night. This yearly plan would typically remain fairly accurate.


However, the situation has changed dramatically. As we discussed earlier, weather patterns have become much more unpredictable. Additionally, power markets worldwide are liberalizing, leading to increasingly short- term operations. Depending on the region, we now see not just day-ahead markets, but also intraday markets and grid ancillary services. Some of these markets operate on 15-minute intervals or even shorter timeframes. This new landscape makes it extremely challenging


to make optimal decisions in real-time, 24 hours a day, without the support of machine learning. That’s why we developed our proprietary intelligent planning algorithm called HIRO. This algorithm is designed to support users in navigating these complex decisions. A key feature of our algorithm is its versatility. It can manage everything from simple run-of-river


Above and left: There have been many changes in the control room of hydropower plants over the year but the basic concept remains the same: it’s the central hub for real-time management of hydropower plants


www.waterpowermagazine.com | September 2024 | 11


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53