PRE2023 1 Group1

Group members

Name	Student number	Major
Sven Bendermacher	1726803	BAP
Marijn Bikker	1378392	BAP
Jules van Gisteren	1635530	BAP
Lin Wolter	1726927	BAP

Problem statement

The problem that will be addressed in this project is the development of an algorithm that finds the moment the price for electricity is the lowest for electric devices, reducing the amount of money one loses to its yearly electricity bill. With the variable fee of the energy contract, the timing of the use of your electric device matters for the price one pays for the electricity. At moments when the energy generation exceeds the demand of electricity, the price will be low. An smart algorithm putting on the dish washer or washing machine at the moment the price is the best during the night could be profitable. Today, people can already take advantage of the hourly fluctuating prices by watching the costs of a kilowatt in an app, and then setting the time of an high electricity demanding device at an inexpensive moment. This is a practice for some people, but not everyone likes put in the effort to do this consistently. For those this algortihm combined with an app that does the work for you can come in handy, in particular if the algoritm can be connected to smart electric devices to operate them, making sure the system operates on its own without the need of human activity.

New problem statement:

With the emerging of more renewable energy and of more energy intensive technologies, like airconditionings needed due to rising temperatures and more extreme weather, the electricity landscape has changed. The increase in load on the electricity net has to be counteracted by either improvements of the network or measures to decrease the peakload on the net. Next to this consumers often pay high prices for electricity due to producers having to power on fossil fuel plants to reach the electricity production needed for the peak times of the day, while sometimes renewable electricity is lost due to lack of use during high sun low use times. To fix this problem producers and governments have turned to introducing dynamic electricity contracts, where consumers pay different amounts of money depending on the time of consumption, thus making it more financially wise to use electricity on the low peak times. This usage of the electricity on different times can even lead to profits on the end of the consumer, and helps the planet and producers to increase the share of renewable sources of electricity. The dynamic electricity contract needs, at the moment, still a large amount of effort and input from the consumer to achieve the promised savings on electricity bills. And this thus leads to less people switching over to a dynamic electricity contract hampering the decrease of load on the net.

Project Requirements, Preferences, and Constraints

Creating RPC criteria

Setting requirements

It is necessary to work for the algorithm that it has access to the prices of the electricity per hour for the coming 24 hours. This way the algorithm can do its math and calculate the best moments for the electric devices. Therefore, the algorithm will need connection to Wi-Fi, to download the most up to date data. Algorithm should be reliable. Not too many bugs should occur, since this would decrease the user-experience drastically.

Setting preferences

The app would ideally be connected to the electric devices. This way a human would not have to interfere with the process and would not be bothered by manually planning the start of the dishwashing or washing machine. Furthermore an app that is easy to use ensures all people can profit from it, also elderly with less expertise regarding mobile phones.

Setting constraints

The app should not be too expensive. Since we are working with small ranges of profit, a too expensive app would not be worth the costs. Another constraint could be the reliance on an electric device being ready. If the dish washer is not ready for use yet, the app can not be used.

RPC-list

Requirements

• Implementable
  • Relatively cheap
  • No infrastructural changes in the electric circuit for a device that is able to turn on electric device
  • Algorithm should be reliable
• Access to data regarding electricity prices
• connection to Wi-Fi

Preferences

• User feedback/interaction
  • App should be easy to use
  • App is looking good
  • App tracking the total amount of saved money
• Connection to the electric devices

Constraints

• Environment (house)
  • Not-smart electric devices
  • Moment the electric devices are not ready to be used.

Users

The possible users for the algorithm for low energy pricing are quite vast, ranging from private homeowners to businesses. Private homeowners can use this app to lower their expenses on energy, which is especially important due to the surge in energy prices due to everything happening in geopolitics. Homeowners could thus use this to turn on their appliances at the right times leading to huge chances on saving large sums of money. Next to private homeowners even factories or businesses could look into using the algorithm, their sometimes-intensive use of energy could then also be better placed at more beneficial times. Energy intensive procedures needed to for example fabricate a certain product could then be done at better times lowering the costs of production leading to higher profits, which is in capitalism of course one of the main drivers in business. Thus, the users for the algorithm spread almost everyone, since almost no one lives without using electricity in this current era.

Private homeowners

As described above one of the most important users would be private homeowners, since the developed app/algorithm would enable them to save large sums of money. This users most important wish would encompass mostly a good working app which is easy to navigate as well as a trustable algorithm. The algorithm should be trustable since if the algorithm is wrong very often there would be no need to use the app, some errors can be accepted though since in no case would using the app cost more money than when using electricity on chosen times, only a perfect human being would be able to spread the electricity usage better than the algorithm.

Companies

The companies would similarly to the homeowners also want a good working app, with again a huge focus on the accuracy of the algorithm. Companies would also benefit from other built in functions such as overviews of electricty use as well as a method to make sure the responsible people are informed, which should thus need everyone to be connected to a single account. Companies would thus make profit from the use of the app/algorithm but would not need major alterations to the normal version for private homeowners.

Other institutions

Since the use of electricity is such a general thing in life, any group of people, company or institution having control over their electricity use could use the app to lower their electricty prices. An important question that then arises however is, in the case that many people start using the app, can the algorithm adapt to correctly spread the use of electricity. Since the increase in usage would also lead to an increase in electricity use on times that would otherwise be seen as off peak.

Other uses

Next to the intended uses done by users as desribed above it is important to mention that with a app based on a great algorithm other interests could also arise. If the algorithm is made to be very accurate with forecasts further into the future, as little as one day, people could start to make money using the app, since some platforms may enable users to trade electricity. This trading of electricity would increase prices and is in the scope of the perceived app not to be wished, since the proposed function of the app is to reduce costs and increase sustainability not to create profits for certain people.

Deliverables

The deliverables of this project will exist of an algorithm that is implanted in an app. This algorithm will be substantiated with documentation in which a literature review is embedded and the capabilities/results of the algorithm will be compared with other energy pricing options.

State-of-the-art

Papers on algorithms for optimal energy consumption.

• Dynamic energy scheduling and routing of a large fleet of electric vehicles using multi-agent reinforcement learning.
• Residential demand response: Dynamic energy management and time-varying electricity pricing.
• Implementation of a dynamic energy management system using real time pricing and local renewable energy generation forecasts.
• Impact of dynamic energy pricing schemes on a novel multi-user home energy management system.
• Research on consumer risks and benefits of dynamic electricity price contracts A risk or an opportunity to save?
• Asset Study on Dynamic retail electricity prices by European commission

Research on consumer risks and benefits of dynamic electricity price contracts A risk or an opportunity to save?

This research states that there is serious risk involved in switching from fixed prices to dynamic prices. It concludes that there is only little room for flexible electric consumption, and that the average dynamic prices in France and Austria were higher in 2021 than the fixed price. Furthermore it is said that for households with an electric vehicle(EV) a dynamic electricity bill could be beneficial, since a EV is the biggest consumer within the flexible electricity consumption activities. However, in this paper it is stated that most of the electric consumption is used for space heating and water heating. In the Netherlands we use natural gas to warm up our homes, so the situation might be different and more profitable for Dutch households.

Asset Study on Dynamic retail electricity prices by European commission

This research says that consumers can significantly decrease their electricity bill by shifting to low price moments. It evaluates different kinds of dynamic pricing options, Real time pricing, time of use up till critical peak pricing. Real time pricing and time of use pricing are the riskiest but yield the highest reward, the critical peak pricing has the lowest risk but yield a lower reward. This research also states that a dynamic pricing leads to a more efficient electric grid, since lower peak demand reduces the losses in the electricity grid. This also results in a lower electricity bill.  Additionally, dynamic prices incentivise demand shifting to times of lower prices which usually indicate times of high intermittent renewable energy resources (RES) feed-in. The use of excess electricity can reduce local congestion and therefore facilitate the integration of RES in the energy system. Therefore it would also be in the interest of the government to promote switching to dynamic prices.

Furthermore it gives an overview of the potential customers for dynamic pricing. With a premium on the electricity prices reducing the maximum prices, up to 90 percent of the costumers could profit from dynamic pricing.

Most important points found in study on consumer preferences of electricity pricing programs

TOU vs RTP. RTP is real time pricing where the user pays based on the real time market prices which change every hour. TOU is time of use pricing where the price is fixed long in advance on a timetable.  

Consumers are fine with using dynamic electricity pricing as long as their daily routine is not affected by it or lead to reductions in their comfort level. When asked about electricity contracts people seem to still prefer a static contract. People tested in a dynamic pricing situation proposed multiple insights. Things like lights, tv, stove were things where the price at that point was not really taken into consideration, since the people thought it would affect their lifestyle too much. Things like dishwashers, washing machines and tumble dryers were used much more at low price times. Due to work however the participants of the test could not always benefit from the low prices and seemed to be less willing to turn on the appliances very early or very late in the day. People also preferred RTP over TOU since RTP made the users feel that they could save more money.  

Via a questionnaire it was found out that most people prefer a constant rate even though the advantages of a dynamic contract were explained thoroughly. The cost-saving expectation was 50 – 150 euro but turned out to only be 20 to 60 euro. Therefore, it is necessary that the other advantage of dynamic pricing, the load shifting, to be explained thoroughly. And the participants expressed a wish for demand automation, thus turning on the appliances at low price times automatically in order to make the dynamic pricing seem worthwhile.  

Most important points found in study on influencing residential electricity consumption with tailored messages

Persuasive technologies are an important method to alter consumer behaviour next to financial benefits. Personalized persuasive technologies work better to stimulate people into doing what is wanted of them. Things like tailored information, personalized content, cooperation and competition are known to be good design principles. Messages to the user should be send at appropriate times and should be managed to not create irritation.  

In a trial done with real household many insights were found by the authors. The program where users could gain more insights next to only SMS messages stating the best time to turn on the appliances was used quite little by the users, the users that did at first often use it proceeded to use it less as the trial went on. The users were happy with being able to see achieved savings as well as being able to see a comparison between real and optimal consumption curves. Users say that an in-home display could have stimulated them even more. Also, next to time and possible savings the rate should also be included in the message sent to the users. It was seen that the washing machines and dryers were shifted most often to accompany electricity savings, while dishwashers the least. Users again brought up a preference for automation. Users finally also mentioned that while they were willing to alter their behaviour it was often hard to do this due to work or other unavailability.  

The authors state that their personalized approach did not lead to a higher willingness to use the program than other untailored approaches used in other experiments. The schedules of the users could be taken into account to better approach users for effective savings. If the savings are only very small other incentives should be possibly used such as a widespread reduction in CO2 emissions.  

A paper from 2021 analysing many papers on electricity price forcasting sets out to find the state-of-the-art electricity price forecasting models, it describes problems that make comparing of different models hard and also state that there is no clear benchmark to check the performance of models to. The paper states that there are three main models, statistical models, machine learning models and hybrid models. The comparison of these 3 is very hard thus leading to the authors stating not one single state-of-the-art method but choosing multiple. For the statistical models the authors decide that the LEAR model is very accurate, while for the machine learning models the DNN model is most state-of-the-art. The hybrid models they state to be not compared enough to other models thus they decide to leave them out of consideration.  

LEAR stands for Lasso Estimated Auto Regressive, where Lasso is a regression analysis method that performs both variable selection as well as regularization, which is useful to increase the quality of the dataset used for the model. Auto regressive just points to the type of model being based on time series analysis.  

DNN stand for Deep Neural Network, which is a type of machine learning with the objective of trying to replicate the way a human brain thinks. The deep part stands for it being multiple levels of machine learning. These models can be better in analysis and prediction than the statistical models but do use much more computing power.  

Appendix

Planning and logbook

Planning

Week	Day	Date	Occasion	Contents
1	Monday	04-09	Instruction meeting	Group formation, Brainstorm about subject
1	Thursday	07-09	Group meeting	Decide on a subject, divide tasks among group members
1	Sunday	10-09	Deadline	Update the wiki on the first progress
2	Monday	11-09	Feedback meeting	Receive feedback on choice of the subject
2	Thursday*	14-09	Group meeting	Brainstorm about what involved parties to contact
2	Sunday	17-09	Deadline	Finish literature study, Write summaries of the literature study on the wiki
3	Monday	18-09	Feedback meeting	Receive feedback on literature study and choice of involved parties
3	Thursday*	21-09	Group meeting	Start working on the product, contact involved parties
3	Sunday	24-09	Deadline	Finish contacting involved parties, update the wiki on the first design/idea of the product
4	Monday	25-09	Feedback meeting	Receive feedback on contact with involved parties and product
4	Thursday*	28-09	Group meeting	Implement information of the involved parties, work on the product
4	Sunday	01-10	Deadline	Update the wiki on the progress
5	Monday	02-10	Feedback meeting	Recieve feedback about the implementation of the information of the involved parties and current version of the product
5	Thursday*	05-10	Group meeting	Implement the feedback, continue working on the product
5	Sunday	08-10	Deadline	Update the wiki on the progress
6	Monday	09-10	Feedback meeting	Receive feedaback on the progress
6	Thursday*	12-10	Group meeting	Work on the first draft of the final version of the wiki and the product
6	Sunday	15-10	Deadline	Finish the first draft of the final version of the wiki and product
7	Monday	16-10	Feedback meeting	Recive feedback on the drafts
7	Thursday*	19-10	Group meeting	Implement feedback, Check each others work, start working on the presentation
7	Sunday	22-10	Deadline	Finish the final version of the wiki and the product, finish the presentation
8	Monday	23-10	Presentation

Logbook

Week	Name	Break-down of hours	Total hours spent
1	Sven Bendermacher	Searing for ideas (2h), Meeting about subject (1h), Writing deliverables section and mail teachers (0.5h), finding/scanning some promising literature [1-4] (2.5h).	6
	Marijn Bikker	Introductory lecture, research into problems and possible technical solution, Meeting about subject, writing problem statement and RPC's.	6
	Jules van Gisteren	Searching for ideas (1.5h), Preparing meeting (0.5h), Meeting about subject (1h), Creating the logbook and planning (2h)	5
	Lin Wolter	Searching for ideas (2.5h), Looking into possible users (2h), Start of literature study with writing of State-of-the-art (3.5h)	8
2	Sven Bendermacher
	Marijn Bikker	Meeting with tutors, working together on problem, literature study, meeting.	4,5
	Jules van Gisteren
	Lin Wolter
3	Sven Bendermacher
	Marijn Bikker
	Jules van Gisteren
	Lin Wolter
4	Sven Bendermacher
	Marijn Bikker
	Jules van Gisteren
	Lin Wolter
5	Sven Bendermacher
	Marijn Bikker
	Jules van Gisteren
	Lin Wolter
6	Sven Bendermacher
	Marijn Bikker
	Jules van Gisteren
	Lin Wolter
7	Sven Bendermacher
	Marijn Bikker
	Jules van Gisteren
	Lin Wolter
8	Sven Bendermacher
	Marijn Bikker
	Jules van Gisteren
	Lin Wolter

Approach

• Literature study
• Contacting involved parties, interviews