Charilaos holds a PhD degree at Electrical and Computer Engineering (Technical University of Crete, 2017). He also received an MSc in Electrical and Computer Engineering at the same institution (2013), and completed his undergraduate studies as a Computer Engineer in the Computer Engineering and Informatics Department at the University of Patras in 2011.
His research topics include Mechanism Design, Multiagent Learning methods, Internet of Things, Blockchain technology, and Artificial Intelligence with applications to the Smart Grid. He currently works as a postdoctoral researcher at NCSR “Demokritos”.
In the past, apart from taking part in a number of research projects, he also taught the "COMP-417 Artificial Intelligence" undergraduate course at the School of ECE TUC, during 2018, and currently co-teaches the postgraduate course "Applied Data Science" of the MSc in Data Science (University of Peloponnese and NCSR "Demokritos").
Member of the Hellenic Artificial Intelligence Society (EETN) and of the Technical Chamber of Greece (TEE).
20. Sotirios Evangelou and Charilaos Akasiadis (2020). SECURITY ASSESSMENT IN IOT ECOSYSTEMS. In Artificial Intelligence of Things at the core of secure, connected and dependable CPS Workshop, SETN 2020, Athens, Greece, 2-4 September 2020. [Abstract]
The Internet of Things (IoT) and "Smart Everything" trend is a reality that is becoming part of our daily lives. Consequently, there is a gradual increase in the deployment of real world IoT systems that attempt to make use of the various possibilities and benefits the IoT offers. However, the connection of billions of - usually inherently insecure - devices in a network, paired with the lack of a clear security framework for the development of IoT systems and platforms has widened the attack surface of these systems leading to them being targeted by malicious actors. In this paper, we explore the problem and related research, devise an assets taxonomy and focus on the security requirements for each asset category. Then, we provide countermeasures and good practices as well as new approaches based on AI that improve security and intrusion detection capabilities. We also introduce a metric that can be incorporated by automated security auditing methods. The relevance of this metric is evaluated with respect to correlation across findings from a real-world study.
19. Charilaos Akasiadis, Vassilis Pitsilis, Constantine D. Spyropoulos (2019).
A MULTI-PROTOCOL IOT PLATFORM BASED ON OPEN-SOURCE FRAMEWORKS. Sensors 2019, 19(19), 4217, MDPI. [Abstract]
Internet of Things (IoT) technologies have evolved rapidly during the last decade and many architecture types have been proposed for distributed and interconnected systems. However, most systems are implemented following fragmented approaches for specific application domains, introducing this way difficulties in providing unified solutions. The unification of solutions though, is an important feature from an IoT perspective. In this paper, we present an IoT platform that supports multiple application layer communication protocols (REST/HTTP, MQTT, AMQP, CoAP, Websockets), and is composed of open-source frameworks (RabbitMQ, Ponte, OM2M, RDF4J). We have explored a backend system that interoperates with the various frameworks and offers a single approach for user access control on IoT data streams and microservices. The proposed platform is evaluated using its containerized version, being this way easily deployable on the vast majority of modern computing infrastructures. Its design promotes service reusability, and follows a marketplace architecture, so that the creation of interoperable IoT ecosystems with active contributors is enabled. All the platform's features are analyzed and we discuss the results of experiments, with the multiple communication protocols being tested when used interchangeably for transferring data. Developing unified solutions using our platform is of interest to users and developers as they can test and evaluate local instances, or even complex applications composed of their own IoT resources, before releasing a production version to the marketplace. [pdf]
18. Nikolaos Spanoudakis, Charilaos Akasiadis, Georgios Kechagias, Georgios Chalkiadakis (2019).
AN OPEN MAS SERVICES ARCHITECTURE FOR THE V2G/G2V PROBLEM. In Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS-19) pp. 2198-2200, IFAAMAS, Montreal QC, Canada — May 13 - 17, 2019. [Abstract]
In this paper we propose an original and open multi-agent system architecture for the important and challenging to engineer vehicle-to-grid (V2G) and grid-to-vehicle (G2V) energy transfer problem domain. To address the features required, we define two novel design patterns that can be used with statecharts in many real-world situations. The first one is based on the well-known factory design pattern, and the second on the class generalization relationship. These patterns can be coupled with ASEME, an agent-oriented software engineering methodology that uses statecharts for the inter- and intra-agent control models. The latter also fits well with the FIPA standards-compliant JADE agent platform that we used for implementation. [pdf]
17. Georgios Chalkiadakis, Charilaos Akasiadis, Nikolaos Savvakis, Theocharis Tsoutsos, Thomas Hoppe, Frans Coenen (2018).
PROVIDING A SCIENTIFIC ARM TO RENEWABLE ENERGY COOPERATIVES. The Role of Exergy in Energy and the Environment, Green Energy and Technology, pp. 717-731, Springer. [Abstract]
Renewable Energy-Supplying cooperatives (REScoops) are cooperatives of renewable energy producers and/or consumers, which are under formulation in the emerging European smart grid. Their emergence highlights the importance of proconsuming green energy and simultaneously puts forward principles such as energy democracy and self-consumption, assists the fight against energy poverty, and helps reduce GHG emissions. To this end, the incorporation of scientific and technological solutions into the REScoops’ everyday business and practices, is key for improving these practices and assessing their potential benefits, and as such for enabling them to deliver the maximum possible gains to their members and society at large. This chapter outlines three key axes of scientific research and solutions that can be used for REScoops, namely, (a) a statistical analysis, (b) an applied behavioural analysis, and (c) an artificial intelligence/machine learning one. Also presented are results and lessons learned from providing such solutions to European REScoops as part of the H2020 REScoop Plus project. [pdf]
16. Charilaos Akasiadis and Alexandros Georgogiannis (2017).
PREDICTING AGENT PERFORMANCE IN LARGE-SCALE ELECTRICITY DEMAND SHIFTING. Advances in Building Energy Research 12(1), pp. 116-137, Taylor and Francis. [Abstract]
A variety of multi-agent systems methods has been proposed for forming cooperatives of interconnected agents representing electricity producers or consumers in the Smart Grid. One major problem that arises in this domain is assessing participating agents’ uncertainty, and correctly predicting their future behaviour regarding power consumption shifting actions. In this paper we adopt various machine learning techniques and use these to effectively monitor the trustworthiness of agent statements regarding their final shifting actions. In particular, we evaluate the performance of four approaches, one based on a Histogram Filter, and three on regression approaches, i.e. Gaussian Process, k-Nearest Neighbours, and Kernel Regression. We incorporate these to aggregate individual forecasts within a directly applicable scheme for providing cooperative electricity demand shifting services. Experiments were conducted on real-world datasets from thousands of users located in Kissamos, a municipality of Crete. Our results confirm that the adoption of machine learning techniques provides tangible benefits regarding enhanced cooperative performance, and increased financial gains for the participants. [pdf]
15. Charilaos Akasiadis and Georgios Chalkiadakis (2017).
COOPERATIVE ELECTRICITY CONSUMPTION SHIFTING. Sustainable Energy, Grids and Networks, 9C, pp. 38-58, Elsevier. [Abstract]
In this paper, we propose the formation of agent cooperatives offering large-scale electricity demand shifting services, and put forward a complete framework for their operation. Individuals, represented by rational agents, form cooperatives to offer demand shifting from peak to non-peak intervals, incentivized by the provision of a better electricity price for the consumption of the shifted peak load, similar to economy of scale schemes. We equip the cooperatives with a novel, directly applicable, and effective consumption shifting scheme, that allows for the proactive balancing of electricity supply and demand. Our scheme employs several algorithms to promote the formation of the most effective shifting coalitions. It takes into account the shifting costs of the individuals, and rewards them according to their shifting efficiency. In addition, it employs internal pricing methods that guarantee individual rationality, and allow agents with initially forbidding costs to also contribute to the shifting effort. The truthfulness of agent statements regarding their shifting behavior is ascertained via the incorporation of a strictly proper scoring rule. Moreover, by employing stochastic filtering techniques for effective individual performance monitoring, the scheme is able to better anticipate and tackle the uncertainty surrounding the actual agent shifting actions. We provide a thorough evaluation of our approach on a simulations setting constructed over a real-world dataset. Our results clearly demonstrate the benefits arising from the use of agent cooperatives in this domain. [pdf]
14. Grigorios Tzortzis, Charilaos Akasiadis and Evaggelos Spyrou (2017).
SEMANTIC COMPLEX SERVICE COMPOSITION WITHIN AN IoT ECOSYSTEM. The Internet of Things: Foundation for Smart Cities, e-Health and Ubiquitous Computing, pp. 151-172, CRC Press. [Abstract]
During the last few years, advances in single board computers, communications technologies and efficient protocols have boosted the emergence of the Internet of Things (IoT). Applications and systems that have been designed to conform to the IoT principles typically follow a service-oriented architecture (SoA). Consequently, billions of devices have been interconnected and integrated as modular web services. The latter can be used and re-used by developers to build complex applications, significantly increasing the interest on service composition techniques. In this chapter the SYNAISTHISI IoT-ready platform is utilized, where available services are semantically annotated and can be readily mashed into applications. The platform uses an ontology for attaching semantic content to services typically found in a smart meeting room. Based on this ontology, an analysis of the process of service composition from a developer's perspective is presented. This can be made possible either by using a manual, or and a semi-automatic service composition approach. To demonstrate the workflow of the two approaches, a real-world case is presented: The creation of a complex application that counts the number of persons present within a smart meeting room, by interconnecting simpler, IoT-enabled services. [pdf]
13. Charilaos Akasiadis and Georgios Chalkiadakis (2017).
MECHANISM DESIGN FOR DEMAND-SIDE MANAGEMENT. IEEE Intelligent Systems 32:1, pp. 24-31. [Abstract]
As the penetration of renewables into the Grid increases, so do the uncertainty and constraints that need to be taken into account during demand-side management (DSM). Mechanism design (MD) provides effective DSM solutions that incorporate end-users’ preferences and uncertain capabilities, without jeopardizing their comfort. Here we discuss the state of the art in DSM methods, which we broadly classify as game theoretic (largely MD) and not. We then proceed to outline a novel scheme for largescale coordinated demand shifting, a highly important problem. Our mechanism employs the services of cooperatives of electricity consumers; it incentivizes truthfulness regarding the contributions promised by the participants; incorporates profiling techniques that assess the contributors’ trustworthiness; and is shown via simulations over real-world datasets to effectively shift peak load and generate substantial economic benefits at cooperative and individual level.
12. Frans Coenen, Thomas Hoppe, Georgios Chalkiadakis, Theocharis Tsoutsos, Charilaos Akasiadis (2017).
EXPLORING ENERGY SAVING POLICY MEASURES BY RENEWABLE ENERGY SUPPLYING COOPERATIVES (RESCOOPS). In ECEEE 2017 Summer Study on Energy Efficiency, pp. 381-391, Presqu’île de Giens, France, May
Cooperatives for renewable energy supply (REScoops) provide their members renewably generated energy within a cooperative model that enables members to co-decide on the cooperative’s future. REScoops do not only collectively own renewable energy production facilities and supply this to their members, they also use their specific position as energy suppliers to take several actions to persuade their members to save energy. Although the activities that REScoops undertake to some extent resemble those of other organizations, because of their particular organisational and business model as citizens initiatives, the cooperative model, REScoops are supposed to be very well positioned for activities to influence and help their members to save energy. The paper discusses arguments why the REScoop model in energy supply can be an important contributor to reduce energy use by their members. Further this paper discusses measures that have been undertaken by REScoops studied in the REScoop Plus project. We use some illustrative examples to discuss if REScoops are in a relatively good position to take certain measures and succeed in persuading customers to lower their energy consumption level and elaborate on future experiments to explore the proposition that REScoop members save more energy due to actions of these REScoops towards their members.
11. Charilaos Akasiadis, Georgios Chalkiadakis, Michail Mamakos, Nikolaos Savvakis, Theocharis Tsoutsos, Thomas Hoppe, Frans Coenen (2017).
ANALYZING STATISTICALLY THE ENERGY CONSUMPTION AND PRODUCTION PATTERNS OF EUROPEAN RESCOOP MEMBERS: RESULTS FROM THE H2020 PROJECT RESCOOP PLUS. In the 9th International Exergy, Energy and Environment Symposium (IEEES - 9), pp. 372-378, Split, Croatia, May
REScoops are cooperatives of renewable energy producers and/or consumers, which have begun to form in the emerging European Smart Grid. According to the Federation of REScoops in Europe (REScoop.eu), there are currently more than 2,397 REScoops, collectively having more than 650,000 members. As such, their emergence highlights the importance of producing and consuming green energy, and simultaneously puts forward principles such as energy democracy and self-consumption, assists the fight against energy poverty, and reduces GHG emissions. A core objective of the H2020 REScoop Plus project is to promote a better understanding and cultivate the behavioural change of the cooperatives’ engagement. In order for this goal to be met, it was essential to conduct a careful logging of and statistical analysis over the energy data stored by the REScoops, as well as the current state of their engagement in energy efficiency. Such tasks are imperative in order to support the claim that REScoop engagement promotes energy sobriety; and associate consumption reduction with specific behaviours, ICT tools, and EE practices. In this paper, we present the logging and statistical analysis conducted in REScoop Plus, and their results. Specifically, we outline the methodology used for formulating a comprehensive format for collecting the datasets for statistical analysis, a process that involved a lengthy and fruitful interaction with REScoops and their data experts; the extracted requirements for that common format; and the detailed guidelines communicated to the REScoops in order to enable data acquisition and analysis. Finally, we present a summary of the collected data (relating to electricity and heating consumption, demographics, etc.); the detailed statistical analysis process used; and the results of this analysis.
10. Charilaos Akasiadis and Georgios Chalkiadakis (2016).
DECENTRALIZED LARGE-SCALE ELECTRICITY CONSUMPTION SHIFTING BY PROSUMER
COOPERATIVES. In the 22nd European Conference on Artificial
Intelligence (ECAI - 2016), pp. 175-183, The Hague, Netherlands, August-September
In this work we address the problem of coordinated consumption shifting for electricity prosumers. We show that individual optimization with respect to electricity prices does not always lead to minimized costs, thus necessitating a cooperative approach. A prosumer cooperative employs an internal cryptocurrency mechanism for coordinating members decisions and distributing the collectively generated profits. The mechanism generates cryptocoins in a distributed fashion, and awards them to participants according to various criteria, such as contribution impact and accuracy between stated and final shifting actions. In particular, when a scoring rules-based distribution method is employed, participants are incentivized to be accurate. When tested on a large dataset with real-world production and consumption data, our approach is shown to provide incentives for accurate statements and increased economic profits for the cooperative.
[pdf] ---Where we adopt a blockchain-oriented mechanism for the coordination of cooperative members and the sharing of rewards.
9. Charilaos Akasiadis and Georgios Chalkiadakis (2016).
PREDICTING AGENT TRUSTWORTHINESS FOR LARGE-SCALE POWER DEMAND
SHIFTING. In the AI for the Smart Grid Workshop (AI4SG) @ The 9th Hellenic Conference on Artificial Intelligence (SETN-2016).
Thessaloniki, Greece, May 2016. [Abstract]
A variety of multiagent systems methods has been proposed for forming cooperatives of interconnected agents representing electricity producers or consumers in the Smart Grid. One major problem that arises in this domain is assessing participating agents’ uncertainty, and correctly predicting their future behaviour regarding power consumption shifting actions. In this paper we adopt two stochastic filtering techniques, a Gaussian Process Filter and a Histogram Filter, and use these to effectively monitor the trustworthiness of agent statements regarding their final shifting actions. We incorporate these within a directly applicable scheme for providing electricity demand management services. Experiments were conducted on real-world consumption datasets from Kissamos, a municipality of Crete. Our results confirm that these techniques provide tangible benefits regarding enhanced consumption reduction performance, and increased financial gains for the cooperative.
8. Giorgos Sfikas, Charilaos Akasiadis and Evaggelos Spyrou (2016).
CREATING A SMART ROOM USING AN IoT APPROACH.
In the AI for the Internet of Things Workshop (AI-IoT) @ The 9th Hellenic Conference on Artificial Intelligence
Thessaloniki, Greece, May 2016. [Abstract]
In this paper, we present one of the pilot applications of the SYNAISTHISI project, whose goal is to transform a typical meeting room to a "smart meeting room". The SYNAISTHISI platform is used to provide the necessary infrastructure to interconnect heterogeneous devices and services over heterogeneous networks. In the presented case, multiple sensing, processing and actuation units have been developed and deployed. The room's state is continuously monitored and either manually, or remotely, or even through automatic processes, decisions are made to control the room lights, cooling, heating, and projector operation. For example, when a meeting is scheduled, the lights and the projector turn on automatically. During the meeting session, environmental measurements (temperature, humidity and ambient light), energy consumption measurements and estimations of the number of people present are collected. Maintaining comfort levels for room occupants is achieved through automatic rule-based decision making. In order to evaluate our approach we follow a qualitative evaluation performed by real-life users of the Smart Room.
7. Charilaos Akasiadis, Grigorios Tzortzis, Evaggelos Spyrou and
Constantine Spyropoulos (2015).
DEVELOPING COMPLEX SERVICES IN AN IoT ECOSYSTEM. In the 2015 IEEE World Forum
on Internet of Things (WF-IoT 2015), pp. 52-56, Milan, Italy, December 2015. [Abstract]
Recent advancements in single board computers, communications technologies and protocols, as well as the concepts of service-oriented architectures (SoA) and everything as a service (EaaS), constitute a prelude to the Internet of Things (IoT) revolution. Billions of devices are interconnected and integrated as modular web services, which can be used and re-used by developers making the building and realization of complex applications easier. In this work, we take advantage of the SYNAISTHISI platform, which is able to interface and integrate devices, services and humans, and expose their capabilities as virtualized semantically annotated services that can be mashed into applications. We analyze the development process from a developer’s perspective, present an ontology for smart meeting rooms and focus on a real-world case, that is delivering a complex application for counting the persons in the interior of a smart meeting room, using technologies that support IoT.
6. Charilaos Akasiadis, Kakia Panagidi, Nikolaos Panagiotou, Paolo
Sernani, April Morton, Ioannis
A. Vetsikas, Lora Mavrouli, Konstantinos Goutsias (2015). INCENTIVES FOR RESCHEDULING
RESIDENTIAL ELECTRICITY CONSUMPTION TO PROMOTE RENEWABLE ENERGY
USAGE. In the SAI Intelligent Systems Conference (IntelliSys 2015), pp. 328-337, London, UK, November
Managing energy consumption and production is a challenging problem and proactive balancing between the amount of electricity produced and consumed is needed. In this work, we examine mechanisms that give incentives to consumers to efficiently reschedule their demand, thus balancing the overall energy production and consumption. Viewing the smart grid as a MAS, each agent represents a consumer; this agent takes into account its user’s preferences and proposes an optimal energy consumption plan via a gamified GUI. To implement this we propose a distributed architecture through which we give the incentives (either economic, or social); we test a number of pricing mechanisms and we develop a very fast agent optimization strategy. We also present experiments both from software simu- lations on real data and pilot tests with human participants: the simulations allow to evaluate the mechanisms and agents, whilst the gamified tests are useful to assess the usability of the GUI and the usefulness of the agent suggestions. With human subjects, we evaluated which type of incentives is more compelling: economic or social. Results validate that by using our agent optimization approach the performance of the smart grid can be improved, and that specific mechanisms allow better utilization of renewable sources.
5. Charilaos Akasiadis, Evaggelos Spyrou, Georgios Pierris,
Dimitris Sgouropoulos, Giorgos Siantikos,
Alexandros Mavrommatis, Costas Vrakopoulos and Theodore Giannakopoulos (2015). EXPLOITING
FUTURE INTERNET TECHNOLOGIES: THE SMART ROOM CASE. In the 8th International Conference on PErvasive Technologies Related to Assistive
(PETRA ’15), pp. 85-86, Corfu, Greece, July 2015. [Abstract]
In this paper we present SYNAISTHISI, i.e., a cloud-based platform, that provides the necessary infrastructure in order to interconnect heterogeneous devices and services over heterogeneous networks. SYNAISTHISI facilitates the orchestration of a collective functionality allowing several services to be managed through agents that dynamically allocate the available resources.. In a smart room use-case, multiple sensing and actuation units have been developed and deployed in a lecture room. Maintaining comfort levels for room occupants is achieved through automatic decision making that exploits information from a complex event recognition engine. Our goal is to improve the overall working environment, while minimizing energy losses.
4. Charilaos Akasiadis and Ioannis A. Vetsikas (2015). A DATASET
GENERATOR FOR EVALUATING
RESOURCE ALLOCATION ALGORITHMS. In the Agent-Mediated Electronic Commerce
and Trading Agent Design and Analysis (AMEC/TADA 2015) AAMAS’15 Workshop, Istanbul,
May 2015. [Abstract]
Lately, the concept of cyber physical systems has emerged. In such settings, various service types, provided either by electronic or biological entities, can be combined and offered to users as on-demand complex applications. To achieve this, customers submit bid bundles describing the requested features of each one of the services. Then, the system searches for the most appropriate and eligible ones, and offers a combination that is able to deliver the requested application. The sets of services and bid bundles are expected to be quite large, and new methods are needed to tackle the complexity. However, since the problem is new, no datasets exist that describe such settings, and thus the methods cannot be compared in a fair manner. For this reason we develop a fully configurable algorithm that can generate realistic datasets, i.e. sets of services and bid bundles holding requests for service subsets that form complex applications. The user can configure parameters regarding service-bid generation, and also the relationships governing them, by selecting specific probabilistic distributions. Our aim is to provide the community with sample datasets and allow the fair comparison of negotiation and various resource allocation methods with respect to their efficiency and behavior. We give a thorough description of the algorithm, and a preliminary analysis of a sample generated dataset.
3. Charilaos Akasiadis and Georgios Chalkiadakis (2014).
STOCHASTIC FILTERING METHODS
FOR PERDICTING AGENT PERFORMANCE IN THE SMART GRID. In ECAI 2014 - 21st
European Conference on Artificial Intelligence- Including Prestigious Applications of Intelligent
Systems (PAIS 2014), pp. 1205-1206, Prague, Czech Republic, August 2014. [Abstract]
A variety of multiagent systems methods has been proposed for forming cooperatives of interconnected agents representing electricity producers or consumers in the Smart Grid. One major problem that arises in this domain is assessing participating agents uncertainty, and correctly predicting their future behaviour. In this paper, we adopt two stochastic filtering techniques —the Unscented Kalman Filter equipped with Gaussian Processes, and the Histogram Filter— and use these to effectively monitor the trustworthiness of agent statements regarding their final actions. The methods are incorporated within a directly applicable scheme for providing electricity demand management services. Simulation results confirm that these techniques provide tangible benefits regarding enhanced consumption reduction performance, and increased financial gains.
2. Charilaos Akasiadis and Georgios Chalkiadakis (2013). AGENT
COOPERATIVES FOR EFFECTIVE
POWER CONSUMPTION SHIFTING. In the 27th AAAI Conference
on Artificial Intelligence (AAAI-2013), pp. 1263-1269, Bellevue, WA, USA, July 2013. [Abstract]
In this paper, we present a directly applicable scheme for electricity consumption shifting and effective demand curve flattening. The scheme can employ the services of either individual or cooperating consumer agents alike. Agents participating in the scheme, however, are motivated to form cooperatives, in order to reduce their electricity bills via lower group prices granted for sizable consumption shifting from high to low demand time intervals. The scheme takes into account individual costs, and uses a strictly proper scoring rule to reward contributors according to efficiency. Cooperative members, in particular, can attain variable reduced electricity price rates, given their different load shifting capabilities. This allows even agents with initially forbidding shifting costs to participate in the scheme, and is achieved by a weakly budget-balanced, truthful reward sharing mechanism. We provide four variants of this approach, and evaluate it experimentally.
1. Perlis V., Akasiadis C., Theofilatos K., N. Beligiannis
G. and D. Lykothanasis S. (2011). APPLYING
COMPUTATIONAL INTELLIGENCE APPROACHES TO THE STAFF SCHEDULING
PROBLEM. In the International Conference on Evolutionary Computation Theory
and Applications (ECTA-2011), pp. 168-173, Paris, France, October 2011. [Abstract]
Staff scheduling for public organizations and institutions is an NP-hard problem and many heuristic optimization approaches have already been developed to solve it. In the present paper, we present two meta-heuristic computational intelligence approaches (Genetic Algorithms and Particle Swarm Optimization) for solving the Staff scheduling problem. A general model for the problem is introduced and it can be used to express most of real-life preferences and employee requirements or work regulations and cases that do not include overlapping shifts. The Genetic Algorithm (GA) is parameterized, giving the user the opportunity to apply many different kinds of genetic operators and adjust their probabilities. Classical Particle Swarm Optimization (PSO) is modified in order to be applicable in such problems, a mutation operator has been added and the produced PSO variation is named dPSOmo (discrete Particle Swarm Optimization with mutation operator). Both methods are tested in three different cases, giving acceptable results, with the dPSOmo outperforming significantly the GA approach. The PSO variation results are very promising, encouraging further research efforts.
Charilaos Akasiadis (2017). Multiagent Demand-Side Management for Real-World Energy Cooperatives. Doctoral Dissertation, School of Electrical and Computer Engineering, Technical University of Crete, Chania, Greece, October 2017. [Abstract]
Balancing energy demand and production in modern Smart Grids with increased penetration of intermittent renewable energy resources is a challenging problem. Demand-Side Management (DSM), i.e., the design and application of sophisticated mechanisms for managing and coordinating energy demand, has been hailed as a means to deal with this problem. In this dissertation, we propose mechanisms for the formation of agent cooperatives offering large-scale DSM services, and put forward a complete framework for their operation. Individuals, being either mere consumers, or even prosumers of electricity, are represented by rational agents and form coalitions to offer demand shifting from peak to non-peak intervals. For cooperatives of consumers, we present an effective consumption shifting scheme, equipped with desirable guarantees, such as individual rationality, truthfulness, and (weak) budget balance. Our scheme employs several algorithms to promote the formation of the most effective shifting coalitions. It takes into account the shifting costs of the individuals, and rewards them according to their shifting efficiency. In addition, it employs internal pricing methods that guarantee individual rationality, and allow agents with initially forbidding costs to also contribute to the shifting effort. The truthfulness of agent statements regarding their shifting behaviour is ascertained via the incorporation of a strictly proper scoring rule. We provide a thorough evaluation of our approach on a simulations setting constructed over a real-world dataset. Our simulation results clearly demonstrate the benefits arising from the use of agent cooperatives in this domain. Moreover, to also allow the decentralized coordination of cooperatives of prosumers, we combine, for the first time in the literature, a strictly proper scoring rule with a specialized cryptocurrency framework. Using our approach, prosumers collaborate with the use of a blockchain-oriented framework to manage their demand, in order to make more profits from the selling of their energy. When tested on a simulation setting that uses dynamic electricity pricing to promote the usage of locally generated renewable energy, our approach drives the prosumers to become more engaged in DSM and achieve increased profits; the balancing of demand and local renewable supply is more effective; and dynamic electricity prices are more stable. Furthermore, we propose a vehicle-to-grid/grid-to-vehicle (V2G/G2V) algorithm that balances demand and local renewable supply in environments populated with electric vehicles. The approach promotes new business models that make effective use of the capability of electric vehicles to store energy in their batteries. Additionally, to assess participating agents’ uncertainty, and correctly predict their future behaviour regarding power consumption shifting actions, promoting in this way accuracy and effectiveness, we adopt various machine learning techniques, adapt them to fit the problem domain, and use these to effectively monitor the trustworthiness of agent statements regarding their final shifting actions. Simulation results confirm that the adoption of machine learning techniques provides tangible benefits regarding enhanced cooperative performance, and increased financial gains for the participants. Finally, we provide the methodology for delivering large-scale DSM services in the real world. To this purpose, we devise an IoT service-oriented architecture for DSM applications, through which we test different GUIs and incentive types for managing energy consumption. In this context, we present a “serious game” solution that was tested by real human subjects. Our approach comes complete with the adoption of a statistical analysis methodology to validate reductions in consumption and the promotion of renewable energy usage in real world settings. Our results show that using the proposed methods in real-world large-scale settings can significantly benefit the end-users, the Grid, and the environment. The success of our approach indicates that the combination of methods from multiple fields of Computer Science can deliver high quality human-centered solutions to complex real-world problems.
Charilaos Akasiadis (2013). A Novel Electricity Demand Management Scheme via Multiagent Cooperatives in the Smart Grid. MSc Thesis, School of Electronic and Computer Engineering, Technical University of Crete, Chania, Greece, December 2013. [Abstract]
In this work, we present a directly applicable scheme for power consumption shifting, and the effective flattening of the electricity consumption curve corresponding to some future date (e.g., the day ahead). It is a pro-active scheme, rather than a last-minute peak trimming one; and it can employ the services of either individual or cooperating consumer agents alike. Agents participating in the scheme, however, are motivated to form cooperatives, in order to reduce their electricity bills via lower group prices granted for sizable consumption shifting from high to low demand time intervals. The scheme takes into account individual costs, and uses a strictly proper scoring rule to reward contributors according to efficiency. Cooperative members, in particular, can attain variable reduced electricity price rates, given their different load-shifting capabilities. This allows even agents with initially forbidding shifting costs to participate in the scheme, and is achieved by a weakly budget-balanced, truthful reward sharing mechanism. We provide four variants of this approach, and evaluate them experimentally. One major problem arising in this domain is assessing the participating agents’ uncertainty, and correctly predicting their future behavior. Thus, in this work we adopt two stochastic filtering techniques, the Unscented Kalman Filter and the Histogram Filter, and use them to effectively monitor the trustworthiness of agent statements regarding their final actions. Interestingly, our UKF filter is equipped with a Gaussian Process regression model. We incorporate these techniques within our demand management scheme. Our simulation results confirm that these techniques provide tangible benefits regarding enhanced consumption reduction performance, and increased financial gains for the cooperative.
Charilaos Akasiadis (2011). Design, Analysis, and Implementation of Computational Intelligence Algorithms (Genetic Algorithms) for the Staff Scheduling Problem in Organizations and Large Institutions of Greece. Engineering Diploma Thesis, Computer Engineering and Informatics Department, University of Patras, Patras, Greece, March 2011. [Abstract]
This work deals with the problem of staff scheduling for organizations and institutions, presenting an integrated environment for its definition and resolution. An application with a graphical interface is being developed for the user, which allows the definition of rules and conditions, covering a large number of cases that occur in the real world. For the resolution of each instance of the problem we utilize an adjustable genetic algorithm designed to be applicable in a broad range of cases. To test the algorithm, we use four snapshots which have been solved with different approaches of the literature in the past.