Weekend Read: Artificial opportunities

Artificial intelligence (AI) is hot right now and is finding central applications in homes and businesses as they move from simple grid connections to self-generation, energy storage, electric vehicle (EV) charging, and load-shifting revenue streams. With AI everywhere, what’s the difference between advanced control, via simple algorithms, and true intelligence?

From pv magazine 12/23-01/24

AI might be a buzzword but when it comes to energy management it is currently the only tool that can take huge amounts of data and make meaningful forecasts to optimize the use of renewable energy and storage, especially as EVs proliferate.

Energy startup Lade, based in Mainz, Germany, focuses on optimizing renewable energy consumption across EV charging and energy management. AI is already proving to be a useful tool deployed for customers’ benefits.

Lade founder and chief executive officer (CEO) Dennis Schulmeyer told pv magazine that an internal team of seven dedicated employees is working on AI in combination with the company’s LADEgenius product, that can handle 200 EV chargers, to interface with local data inputs from PV modules, energy storage systems, and EV chargers, along with inputs and outputs to fulfil grid regulations. LADEgenius is basically an on-site load manager and connector that can make decisions with the help of cloud intelligence. That cloud intelligence uses AI and machine learning, via a system the company calls Lana.

“Lana is AI because she is able to forecast the availability of energy,” said Schulmeyer. “Lana can gather data from weather services in Germany and forecast up to five days to ascertain how much renewable energy will be available.

“We also forecast the availability of local renewable energy for the building, for generation, reading inverter data and weather values for the installation, and forecast consumption as well. Our main [unique selling point] is also being able to forecast car arrival and departure times and how much energy the cars will really need up to five days into the future, and [we] calculate the optimal charge plan for that time.”

All of that comes at a “high cost,” said Schulmeyer, as the AI trains on data and runs on models hosted on cloud servers, with Lade adding some additional costs for itself by paying for the use of strictly renewable energy, with offsets for the servers.

“Our internal team developed the AI for the past three years,” said the CEO. “We initially trained it to use open-source data while adding real data from our chargers and, for example, data from customers from their PV generation, and even our own real-world setup here in Mainz.” Schulmeyer confirmed that adding additional customer data to Lana’s training data has improved predictions further.

Optimizing with AI

SolarEdge’s product vice president, Ido Ginodi, explained how AI is being used to optimize energy management systems and how it handles fundamentally tough optimization problems and forecasting in a way that traditional control algorithms cannot – even in the home. Israel-based SolarEdge is well known in the PV industry and as complexity emerges between energy generation and storage, EV charging, data, and forecasting, Ginodi showed considerable enthusiasm for how his company is using AI’s advantages. “The lines between good solid algorithm approaches and AI are blurry,” Ginodi said. “But after spending a few years researching AI in academic settings, a lot of what people are doing, including us, in this field is truly AI-driven and it promotes our ability to offer state of the art energy optimization.” Ginodi explained that AI is not only required when an application grows in size from a single dwelling, with just one EV charger, to multi-dwelling buildings and commercial and industrial sites with multiple, possibly hundreds, of chargers. “I actually want to argue something a bit different: In the residential use case, AI is extremely important,” said Ginodi. “The problem of energy management is fundamentally a tough optimization problem. We started our journey with the concept of power optimization, optimizing the amount of juice that can be squeezed out of solar arrays. Now we are taking it a few steps ahead, optimizing a whole-site performance, which is an order of magnitude more complex.” The SolarEdge executive explained that an energy management system can optimize metrics for the end customer’s benefit. It does so while orchestrating elements such as PV generation, battery dispatch, EV charging, and load orchestration. Systems can also optimize heating, ventilation, and air conditioning integration for pre-heating and cooling, while accommodating dynamic tariffs and market participation, and even preparations for outages, by using data to make decisions. “It ends up having multiple degrees of flexibility,” said Ginodi. “It’s a lot and it’s fascinating, and in some places AI-driven solutions may generate results that are significantly better than what a naive algorithmic approach could have achieved. But we go further. We develop predictive models based on machine-learning regression techniques for consumption, production, import and export tariffs, and one for grid events. Once you have those four models, you can have classical algorithms make the decision on how you want to dispatch the different resources you have in a system.” For the end user, this translates to the management system either optimizing for profit, as is common, or optimizing for convenience or for decarbonization, per user preferences. Ginodi added that SolarEdge portfolio companies also work closely to incorporate AI capabilities into its offering. In particular, EV charging management company Wevo works to cost-effectively scale EV charging with predictive load management and capacity management. While static and dynamic load management technology is becoming more abundant in the industry, AI in the form of predictive modeling offers significant improvements to the concurrency factor – that is, the ability to fit more chargers under a given grid connection point. “Say an enterprise wants to offer electrified parking spots in its car park,” said Ginodi. “It’s extremely costly to offer 100 new spots at 11/22 kW each. That’s 1 MW or 2 MW of extra power required. A brute force approach would be to require the full power provisioned for the system but you don’t have to charge the vehicles together and you don’t even have to statically attach capacity to each charger. That’s dynamic load management. One step further, you can incorporate the predictions Wevo generate and build an optimal schedule for charging. The model assumes that cars will appear in a parking lot at a certain velocity and what will be the levels of local production and total consumption at each point in time. “With these predictions at hand, one can serve more vehicles and drivers. Up to 20 times more, compared to a naïve implementation.”

Schulmeyer said that advanced software-based controls may solve some problems for a single-dwelling situation but standard equipped-load managers and PV surplus charging systems will soon struggle to deliver real advantages when considering multiple EV chargers. “This is the showstopper,” he added.

In larger commercial and industrial situations energy management needs to happen across numerous EV chargers to avoid unnecessarily large demand without coordination, which makes the task increasingly complex. This is made even more complex by adding forecasting generation and consumption via weather data while offering features such as peak shaving. This would be impossible to operate without AI technology, said the Lade founder.

Improving

“We do all of this and we’re improving,” he said. “If you connect to our EV chargers for the first time, we say our estimates for the energy the car will need over time will have an accuracy of around 67%, up from a lower starting point. But of course, the more data we have, the better it will be – and the advantage of a startup is that we run many models and AI technologies, and we adapt.”

Schulmeyer was careful to point out advantages for the entire ecosystem that go further than AI. “It’s not only the AI algorithm … it’s how you think as a company,” he said. “We are not alone and we will find ways to include others. Indeed, we’ll add third-party chargers in our cloud, with LADEgenius. But this is important because we are not independent in terms of being the only ones to exist in this area. And our goal, above all, is the energy transition, with the help of electric mobility.”

This post appeared first on PV Magazine.

Share This Post